Faglige interesser
Generell økonometri, paneldataøkonometri, mikroøkonometri, økonometri med latente variable, aggregering og økonometri, helseøkonometri, investeringer: beregning av kapital og produktivitet, offentlig økonomi, husholdningers konsum.
Curriculum Vitae
Undervisning
ECON4160  Econometrics  Modeling and systems estimation
ECON4150  Introductory Econometrics
ECON5101  Advanced Econometrics  Time series
ECON5102  Advanced Econometrics  Microeconometrics
ECON5103  Advanced Econometrics  Panel Data
Utdanning og karriere
 Professor i samfunnsøkonomi, Universitetet i Oslo, 19862013.
 Vitenskapelig medarbeider, Frischsenteret 20092011.
 Vitenskapelig rådgiver og seniorforsker, Statistisk sentralbyrå 19862007
 Seniorforsker, forskningsavdelingen, Statistisk sentralbyrå, 19841986
 Dosent (vikar) i samfunnsøkonomi, Universitetet i Oslo, 19831984
 Seniorforsker, forskningsavdelingen, Statistisk sentralbyrå, 19751983
 Visiting scholar, Institut national de la statistique et des études économiques (INSEE), Paris,1980
 Forsker, forskningsavdelingen, Statistisk sentralbyrå, 19721975
 Konsulent/Førstekonsulent, forskningsavdelingen, Statistisk sentralbyrå, 19701971
 Cand.oecon. Universitetet i Oslo, 1969
 Exam.oecon, Universitetet i Oslo, 1967
Verv
 Associate Editor, Empirical Economics
 Rådgiver for Helseøkonomisk forskningsprogram, Universitetet i Oslo, 20002004
 Undervisningsleder (alle nivå), Økonomisk institutt, Universitetet i Oslo, 20022004
 Medlem av arrangementkomiteen for Econometric Methodology Conference, Oslo, 2003
 Medlem av Norges Banks forskningsråd, 19891994
 Medlem av Modellutvalget, Finansdepartementet, 19821990
 Medlem av programkomiteen for Econometric Society European Meeting, København, 1987
 Medlem av bedømmelseskomiteer for professorater ved Uppsala Universitet og Aarhus Universitet, samt for førsteamanuenisisstilling ved Stockholms Universitet.
 Medlem av ekspertkomite for forskerbedømmelse ved Statistisk sentralbyrå, Norges Bank og Frischsenteret.
 Medlem av ekspertkomite for bedriftsbeskatning under Skattekommisjoneen, 19831984.
Emneord:
Samfunnsøkonomi,
Økonometri
Publikasjoner
 Biørn, Erik & Han, Xuehui: Revisiting the FDI Impact on GDP Growth in ErrorsinVariables Models: a Panel Data GMM Analysis Allowing for Error Memory. Empirical Economics, 53, 2017, 13791398
 Erik Biørn, HildMarte Bjørnsen: What Motivates Farm Couples to Seek Offfarm Labour? A Logit Analysis of Job Transitions. European Review of Agricultural Economics, 42, 2015, 339365
 Erik Biørn: VAR Interpretations of Haavelmo's Market Model of Capital and Investment. Econometric Theory, 31, 2015, 195212.
 Erik Biørn: Panel Data Dynamics with Mismeasured Variables: Modeling and GMM Estimation. Empirical Economics, 48, 2015, 517535.
 Erik Biørn: Estimating SUR Systems with Random Coefficients: The Unbalanced Panel Data Case. Empirical Economics,47, 2014, 451468.
 Anne Line BrettevilleJensen, Erik Biørn and Randi Selmer: Does Screening Participation Affect Cigarette Smokers' Decision to Quit? A Longhorizon Panel Data Analysis. Nordic Studies on Alcohol and Drugs, 2014, 141160.
 Erik Biørn, Simen Gaure, Simen Markussen and Knut Røed: The Rise in Absenteeism: Disentangling the Impacts of Cohort, Age and Time. Journal of Population Economics 26, 2013, 15851608
 Trygve Haavelmo/Translated by Erik Biørn: On Statistical Testing of Hypotheses in Economic Theory. Chapter 25 in The Rise of Econometrics, Volume II, ed. by D. Qin. Routledge, 2013, pp. 6784.
 HildMarte Bjørnsen and Erik Biørn: "Interrelated Labour Decisions of Farm Couples: A Censored Response Analysis of OffFarm Work", Agricultural Economics 41, 2010, 595610.
 Inger Cathrine Kann, Erik Biørn and Hilde Lurås: "Competition in General Practice: Prescriptions to the Elderly in a List Patient System", Journal of Health Economics 29, 2010, 751764.
 Erik Biørn and Geir Godager, "Does Quality Influence Choice of General Practitioner? An Analysis of Matched DoctorPatient Panel Data", Economic Modelling 27, 2010, 842853.
 Erik Biørn, Terje P. Hagen, Tor Iversen and Jon Magnussen, "How Different Are Hospitals' Responses to a Financial Reform? The Impact on Efficiency of ActivityBased Financing", Health Care Management Science 13, 2010, 116.
 Erik Biørn, Økonometriske emner, 3. utgave, Unipub, 2009,
 Erik Biørn and Jayalakshmi Krishnakumar, "Measurement Errors and Simultaneity," Chapter 10 in L. Mátyás and P. Sevestre (eds), The Econometrics of Panel Data. Fundamentals and Recent Developments in Theory and Practice, Springer, 2008.
 Erik Biørn, Økonometriske emner. En videreføring, Unipub, 2008.
 Knut Reidar Wangen and Erik Biørn, "How do consumers switch between close substitutes when price variation is small? The case of cigarette types," Spanish Economic Review 8, 2006, 239253.
 Erik Biørn, Terje Skjerpen and Knut Reidar Wangen, "Can random coefficient CobbDouglas production functions be aggregated to similar macro functions?. Chapter 9 in Badi Baltagi (ed), Panel Data Econometrics: Theoretical Contributions and Empirical Applications, Elsevier, 2006,
 Erik Biørn, "How are SurvivalEfficiency Profiles Related to retirmeent Rates and Capital Vintage Prices?" Chapter 8 in Focus on Economic Growth and Productivity, ed. by L.A. Finley. New York: Nova Science Publishers, 2005, pp. 143186.
 Anne Line BrettevilleJensen and Erik Biørn, "Do prices count? A microeconometric study of illicit drug consumption based on selfreported data," Empirical Economics 29, 2004, 673695.
 Erik Biørn, "Regression systems for unbalanced panel data: A stepwise maximum likelihood procedure," Journal of Econometrics 122, 2004, 281291.
 Erik Biørn and Terje Skjerpen, "Aggregation Biases in Production Functions: A Panel Data Analysis of Translog Models". Research in Economics, 58, 2004, 3157.
 Erik Biørn, "Handling the measurement error problem by means of panel data: Moment methods applied on firm data." Chapter 24 in Bernt Petter Stigum (ed), Econometrics and the Philosophy of Economics. TheoryData Confrontations in Economics, Princeton University Press, 2003,
 Anne Line BrettevilleJensen and Erik Biørn, "Heroin Consumption, Prices and Addiction: A Panel Data Analysis Based on SelfReported Data". Scandinavian Journal of Economics, 105, 2003, 661679.
 Erik Biørn, Terje P. Hagen, Tor Iversen and Jon Magnussen, "The Effect of ActivityBased Financing on Hospital Efficiency: A Panel Data Study of DEA Efficiency Scores 19922000". Health Care Management Science, 6, 2003, 271283.
 Jørgen Aasness, Erik Biørn and Terje Skjerpen, "Distribution of preferences and measurement errors in a disaggregated expenditure system," Econometrics Journal 6, 2003, 373399.
 Erik Biørn, "Panel data with measurement errors: instrumental variables and GMM procedures combining levels and differences," Econometric Reviews 19, 2000, 391424,
 Erik Biørn, "Survival and efficiency curves for capital and the timeageprofile of vintage prices," Empirical Economics 23, 1998, 611633,
 Jørgen Aasness, Erik Biørn and Terje Skjerpen, "Engel functions, panel data, and latent variables," Econometrica 61, 1993, 13951422.
 Erik Biørn, "Taxation, Technology and the User Cost of Capital", Amsterdam: NorthHolland, 1989.
 Erik Biørn and Eilev S. Jansen: "Econometrics of Incomplete CrossSection/TimeSeries Data: Consumer Demand in Norwegian Households" 19751977. Oslo: Central Bureau of Statistics, 1982.
 Erik Biørn: "Analyse av sammenhengen mellom forbruk, inntekt og formue i norske husholdninger". (Analysing the Relationship Between Consumption, Income and Wealth in Norwegian Households) Oslo: Central Bureau of Statistics, 1979.
 Erik Biørn: "Analyse av investeringsatferd: Problemer, metoder og resultater". (Analysing Investment Behaviour: Problems, Methods, and Results.) Oslo: Central Bureau of Statistics, 1979.
Selected recent working papers

Biørn, Erik & Han, Xuehui (2017). Revisiting the FDI impact on GDP growth in errorsinvariables models: a panel data GMM analysis allowing for error memory. Empirical Economics.
ISSN 03777332.
53(4), s 1379 1398 . doi:
10.1007/s0018101612034
Vis sammendrag
GMM estimation of autoregressive equations in errorridden variables with error memory is considered in exploring the impact of foreign direct investment (FDI) on GDP from country panel data, contrasting, inter alia, the manufacturing and the service sector. To evaluate finitesample properties of the methods selected, results from Monte Carlo simulations are reported. Contrary to the previous findings, no negative spillover effects from the service FDI on manufacturing GDP growth are obtained; the estimates indicate a positive effect, while (surprisingly) the effect of service FDI on the serviceGDPgrowth comes out as insignificant. Overall conclusions are: (1) Aggregate FDI has a positive, but insignificant effect on aggregate GDP based on the full country panel; (2) for the developing Asian countries, FDI significantly improves GDP growth; and (3) manufacturing FDI impacts both manufacturing and service GDP growth positively.

Biørn, Erik (2015). Panel data dynamics with mismeasured variables: modeling and GMM estimation. Empirical Economics.
ISSN 03777332.
48(2), s 517 535 . doi:
10.1007/s0018101408021
Vis sammendrag
Generalized Method of Moments (GMM) estimation is discussed under the joint occurrence of fixed effects and random measurement errors in an autoregressive panel data model. Finite memory of measurement errors is allowed for. Two GMM specializations are considered: (i) using instruments (IVs) in levels for a differenced version of the equation and (ii) using IVs in differences for the level version. Index sets for lags and leads are convenient in examining how the potential IVset is affected by changes in the memory pattern. While measurement errors with long memory may give an IVset too small for identification, problems of `IV proliferation' and `weak IVs' may arise unless the panel is short. An application based on data for (logtransformed) capital stock and output from Norwegian manufacturing firms, supplemented with Monte Carlo simulations, to illustrate finite sample biases, is considered. Overall, with respect to bias and IV strength, GMM specialization (ii) seems superior to inference using GMM specialization (i).

Biørn, Erik (2015). VAR Interpretations of Haavelmo's Market Model of Capital and Investment. Econometric Theory.
ISSN 02664666.
31(2), s 195 212 . doi:
10.1017/S0266466614000267

Biørn, Erik & Bjørnsen, HildMarte (2015). What motivates farm couples to seek offfarm labour? A logit analysis of job transitions. European Review of Agricultural Economics.
ISSN 01651587.
42(2), s 339 365 . doi:
10.1093/erae/jbu025
Vis sammendrag
Some labour market consequences of transitions in the agriculture sector are examined by combining 20year unbalanced panel data from Norwegian farm households and logit modeling of transition probabilities. The multidimensionality of the problem follows from two decision makers having four possible choices in each period: the farm operator and spouse can be working fully on the farm or having supplementary outside occupation. Transitions are modeled by five logit models. The most flexible model has a high number of parameters. Overall, the results indicate that transitions have mainly been directed towards the state where both partners work off the farm. An increasing livestock reduces the probability of moving to states with substantial offfarm labour participation. Increasing farm size tends to have the opposite effect. Recent onfarm investments come out with ambiguous effects. Having children seems to motivate operators to withdraw from offfarm labour and spouses to stay in or enter offfarm employment.

Biørn, Erik (2014). Estimating SUR system with random coefficients: The unbalanced panel data case. Empirical Economics.
ISSN 03777332.
47(2), s 451 468 . doi:
10.1007/s001810130753y

BrettevilleJensen, Anne Line; Biørn, Erik & Selmer, Randi (2014). Does screening participation affect cigarette smokers' decision to quit? A longhorizon panel data analysis. Nordic Studies on Alcohol and Drugs.
ISSN 14550725.
31(2), s 141 160 . doi:
10.2478/nsad20140012
Fulltekst i vitenarkiv.
Vis sammendrag
INTRODUCTION: Despite decades of intensive antitobacco initiatives, millions of people are still smoking. The health authorities are seeking new tools and extended knowledge. Screening programs may, in addition to the potential health benefits from early detection of smoking related diseases, also increase smoking cessation among participants. This study examines the effect of screening participation by comparing the smokers’ cessation hazard in screening years to nonscreening years. METHODS: All smokers (n=10,471) participated in a threewave cardiovascular screening and were followed up over a maximum of 14 years. The panel was merged with administrative registers. We used a flexible discretetime duration model to investigate the effect of the screening program while simultaneously accounting for the possible influence of personal characteristics, addiction indicators, economic factors, health status and health changes. Specifically, we examined and compared longterm smokers (LT; smoked ≥25 years) with shortterm (ST; smoked ≤ 5 years) and mediumterm (MT; smoked 1020 years) smokers. RESULTS: We found that 29% of LT smokers quitted smoking during the followup whereas 32% of MT and 48% of ST smokers reported the same. The screening participation years stood out as especially important for all groups. The impact of the first screening was particularly high, and for the first two screenings, the effect was higher for longterm smokers than for the smokers with shorter smoking careers. Receiving an abnormal test result was not associated with a significant increase in cessation hazard for any group of smokers. CONCLUSIONS: The substantial effect of being invited to and participating in a screening appears robust, and may prove useful when discussing future policies for smoking cessation. This paper suggests that further initiatives for consultations with health personnel, in this case through a screening program, could increase the quitting hazard.

Biørn, Erik (2013). On the Statistical Testing of Hypotheses in Economic Theory. Oversettelse av Trygve Haavelmo (1939): Om statistisk "testing" av hypoteser i den økonomiske teori. Lecture, Copenhagen, In Duo Qin (ed.),
The Rise of Econometrics.
Routledge.
ISBN 9780415616782.
25.
s 67
 84

Biørn, Erik; Gaure, Simen; Markussen, Simen & Røed, Knut (2013). The rise in absenteeism: disentangling the impacts of cohort, age and time. Journal of Population Economics.
ISSN 09331433.
26(4), s 1585 1608 . doi:
10.1007/s0014801204032
Vis sammendrag
In recent years, a number of welfare state economies, including Norway, have experienced substantial increases in sickness absence. Using longitudinal individual register data for virtually all Norwegian employees, we examine the remarkable rise since the early 1990s, with emphasis on disentangling the roles of cohort, age, and time. We show that individual ageadjusted absence propensities have risen even more than aggregate absence rates from 1993 to 2005, which casts doubt on the popular hypotheses that the rise was due to the inclusion into the workforce of young or marginal workers with weaker worknorms or poorer health.

Biørn, Erik & Godager, Geir (2010). Does quality influence choice of general practitioner? An analysis of matched doctorpatient panel data. Economic Modelling.
ISSN 02649993.
27(4), s 842 853 . doi:
10.1016/j.econmod.2009.10.016
Vis sammendrag
The impact of quality on the demand facing health care providers has important implications for the industrial organization of health care markets. In this paper we study the consumers' choice of general practitioner (GP), assuming they are unable to observe the true quality of GP services. A panel data set for 484 Norwegian GPs, with summary information on their patient stocks, renders the opportunity to identify and measure the impact of GP quality on the demand, accounting for patient health heterogeneity. We apply a multiequation model in the LISREL format, with GP quality and patient health as latent determinants of demand for GP services. Patient excess mortality rate at the GP level is one indicator of quality. Our results indicate that GP quality has a clear positive effect on demand, even when patient heterogeneity is accounted for.

Biørn, Erik; Hagen, TP; Iversen, Tor & Magnussen, Jon (2010). How different are hospitals' responses to a financial reform? The impact on efficiency of activitybased financing. Health Care Management Science.
ISSN 13869620.
13(1), s 1 16 . doi:
10.1007/s107290099106y

Bjørnsen, Marte & Biørn, Erik (2010). Interrelated labor decisions of farm couples: a censored response analysis of offfarm work. Agricultural Economics.
ISSN 01695150.
41(6), s 595 610 . doi:
10.1111/j.15740862.2010.00475.x
Vis sammendrag
Farm couples' labour market responses are partly the discrete choice of entering the offfarm labour market and partly the continuous choice of offfarm working hours, given entry. Such a setting is interesting when examining the increasing occurrence of multiple jobholdings among farmers in western economies. Most existing analyses of offfarm labour supply only model the decisions of the farmer, not the joint decisions of the farm couple. This paper presents a framework for handling such interrelated discrete/continuous choices, involving also farm production and household consumption. The derived twoequation submodel for husband/wife's censored labour responses is estimated from a 10year Norwegian panel data for 342 farms. The results agree to some extent with earlier studies, but are more informative because of the longer panels  which allows a more extensive examination of latent heterogeneity and behavioural persistence  because it provides crosseffects in the spouses' labour supplies. The results show some interesting differences between how the independent variables influence the labour supply of operator and spouse. This is most evident for the crosseffects of education, children and wage rate. Overall, the results strongly support applying a panel censoring model that accounts for latent heterogeneity in this context.

Kann, Inger Cathrine; Biørn, Erik & Lurås, Hilde (2010). Competition in general practice: Prescriptions to the elderly in a list patient system. Journal of Health Economics.
ISSN 01676296.
29(5), s 751 764 . doi:
10.1016/j.jhealeco.2010.07.004
Vis sammendrag
Income motivation among general practitioners is frequently discussed in the health economics literature. The question addressed in the present study on reimbursement drugs and addictive drugs is whether increased competition among GPs, which is part of a declared health policy to improve efficiency, contributes to more prescriptions for the elderly. The dataset comprises registered data of all prescribed drugs dispensed at pharmacies from the Norwegian Prescription Database merged with data on GPs. In choosing a method, particular attention is given to the fact that patients tend to be attracted to GPs who fit their preferences. Hence, we treat the composition of the patient list as endogenous. The results indicate that the stronger competition a GP faces, the more drugs are prescribed, which implies that GPs' prescription style may conflict with their role as gatekeepers, and even worse, it may be a hazard to patients' health.

Biørn, Erik (2009). Estimation of discrete choice and censoring models (In Russian). Quantile.
ISSN 09998888.
6, s 49 57 Fulltekst i vitenarkiv.
Vis sammendrag
This expository note gives an overview of model specifications, likelihood functions and structure of the Maximum Likelihood problems for discrete choice models and censoring models. One part deals with estimation in the single equation case with unidimensional (crosssectional) observations. Another part extends the framework to a twoequation case. Tha last part is concerned with an extension to a panel data situation.

Biørn, Erik & Krishnakumar, Jayalakshmi (2008). Measurement Errors and Simultaneity, In Laszlo Matyas & Patrick Sevestre (ed.),
The Econometrics of Panel Data. Fundamentals and Recent Developments in Theory and Practice.
Springer.
ISBN 9783540758891.
Chapter 10.
s 323
 367

Biørn, Erik; Skjerpen, Terje & Wangen, Knut R. (2006). Can Random Coefficient CobbDouglas Production Functions be Aggregated to Similar Macro Functions?, In Badi Baltagi (ed.),
Panel Data Econometrics: Theoretical Contributions and Empirical Applications.
Elsevier.
ISBN 0444521720.
Chapter 9.
s 229
 258
Vis sammendrag
Parametric aggregation of heterogeneous micro production technologies is discussed. A fourfactor CobbDouglas function with normally distributed firm specific coefficients and with lognormal inputs (which agrees well with the available data) is specified. Since, if the number of micro units is large enough, aggregates expressed as arithmetic means can be associated with expectations, we consider conditions ensuring an approximate relation of CobbDouglas form to exist between expected output and expected inputs. Similar relations in higherorder moments are also derived. It is shown how the aggregate input elasticities depend on the coefficient heterogeneity and the covariance matrix of the loginput vector and hence vary over time. An implementation based on firm panel data for two manufacturing industries gives estimates of industry level input elasticities and decomposition for expected output. Finally, aggregation errors which emerge when the correct aggregate elasticities are replaced by the expected micro elasticities, are explored.

Biørn, Erik; Skjerpen, Terje & Wangen, Knut Reidar (2006). Can Random Coefficient CobbDouglas Production Functions be Aggregated to Similar Macro Functions?, In Badi Baltagi (ed.),
Panel Data Econometrics: Theoretical Contributions and Empirical Applications.
Elsevier.
ISBN 0444521720.
Chapter 9.
s 229
 258

Wangen, Knut Reidar & Biørn, Erik (2006). How Do Consumers Switch Between Close Substitutes when Price Variation is Small? The Case of Cigarette Types. Spanish Economic Review.
ISSN 14355469.
8(4), s 239 253
Vis sammendrag
Past empirical studies report ambiguous results regarding the magnitude and significance of substitution between different types of smoking tobacco. Since all types of tobacco contain nicotine this is quite surprising. Using a twentyyear rotating panel data set of Norwegian households and a multinomial logit model, we find evidence that consumers switch between tobacco types: first, estimated price effects on choice probabilities have mostly expected signs, albeit their statistical significance vary across different metrics, second, household characteristics affect tobacco composition significantly. These findings suggest that consumers' choices are `locked' when the relative price variation is small, as has been the case in most of the data period, but that larger changes could induce largescale switching between tobacco types. Our conjecture is that there is a latent potential for switching, which will become manifest if prices change sufficiently. Similar considerations are likely to have relevance for other close substitutes.

Biørn, Erik (2005). How Are SurvivalEfficiency Profiles Related to Retirement Rates and Capital Vintage Prices?, In L.A. Finley (ed.),
Focus on Economic Growth and Productivity.
Nova Science Publishers, Inc..
ISBN 1594542724.
Kapittel 8.
s 143
 186
Vis sammendrag
The decline in the service flow from a stock of capital goods with age, due to the physical retirement of capital units and the gradual loss of efficiency of each unit remaining, can be described by survival curves and efficiency curves. We discuss the relationship between the retirement process of the capital, as formalized by these curves, and the average retirement rate, and how this relationship is affected by changes in the investment growth path. The effect of changes in the survival and efficiency curves on the age distribution of the capital goods, those existing as well as those retired in each period, is also considered. We next reconsider the relationship between these curves and the vintage prices of capital under neoclassical assumptions about perfect secondhand markets and malleability, using duality between quantities and prices. Three examples with parametric survival and efficiency curves are presented. The retirement rate is a declining function of the growth rate of investment (except in the exponential decay case) and quite sensitive to this growth rate over a reasonable interval. Approximating the retirement rate by the inverse of the capital's maximal lifetime or twice this value (`double declining balance') will frequently produce very inaccurate results. The response of the capital/investment ratio and the retirement/investment ratio to changes in the investment growth rate and in the curvature of the survival function is also investigated. Concavity of the survival and efficiency curves may be compatible with convexity of the ageprice profile. This approach for making inference on survival and efficiency functions from vintage price data is contrasted with the frequently cited HultenWykoff approach. Our estimates give evidence less strongly in favour of convex efficiency and survival curves than is often believed.

Biørn, Erik & Skjerpen, Terje (2004). Aggregation Biases in Production Functions: A Panel Data Analysis of Translog Models. Research in Economics.
ISSN 10909443.
58(1), s 31 57
Vis sammendrag
The value of panel data for micro units in exploring aggregated relationships empirically is substantial, since such data are not only useful for estimation at both the micro and the macro level, but also allow comparison of properties of relationships aggregated formally from the micro level with those resulting from aggregation by analogy in an informal way. Using panel data from manufacturing plants, we consider biases in the aggregation of the Translog production function, which does not generally satisfy the strict mathematical conditions for perfect aggregation. Linear and loglinear aggregation in the presence of random coefficients are considered. Under linear aggregation across plants, departures between geometric and arithmetic means of inputs as well as correlation between loginputs, contribute substantially not only to biases in the output volume, but also to instability in derived input and scale elasticities and biases in total factor productivity growth. Overall, the biases under loglinear aggregation are smaller.

Biørn, Erik (2004). Regression systems for unbalanced panel data: a stepwise maximum likelihood procedure. Journal of Econometrics.
ISSN 03044076.
122(2), s 281 291
Vis sammendrag
The estimation of systems of regression equations with random individual effects from unbalanced panel data, where the unbalance is due to random attrition or accretion, by Generalized Least Squares (GLS) and Maximum Likelihood (ML) is considered. In order to utilize previous results for the balanced case, it is convenient to arrange the individuals in groups according to the number of times they are observed. It is shown that the GLS estimator can be interpreted as a matrix weighted average of the group specific GLS estimators with weights equal to the inverse of their respective covariance matrices. A stepwise algorithm for solving the ML problem, which can be interpreted as a compromise between the solution to the group specific ML problems, is presented.

BrettevilleJensen, Anne Line & Biørn, Erik (2004). Do Prices Count? A MicroEconometric Study of Illicit Drug Consumption Based on SelfReported Data. Empirical Economics.
ISSN 03777332.
29(3), s 673 695
Vis sammendrag
Using a unique data set of almost 2,500 interviews with people attending a needle exchange service in Oslo, this paper sets out to estimate the impact of economic factors on heroin and amphetamine injectors' drug consumption, including crossprice effects. To examine the robustness of the conclusions, four model versions are considered: with focus on (i) switching regression mechanisms treating dealing/nondealing as an endogenous decision, (ii) spline function versions examining possible `kinks' in the price response, (iii) a dynamic model version focusing on addiction, and (iv) pseudo panel data model versions focusing on unobserved heterogeneity. Negative and significant price elasticities and positive and significant income elasticities come out as robust results. Their magnitude vary, however, depending on the type of model, on the main drug for injecting, and on whether the consumer also is a dealer.

Aasness, Jørgen; Biørn, Erik & Skjerpen, Terje (2003). Distribution of Preferences and Measurement Errors in a Disaggregated Expenditure System. Econometrics Journal.
ISSN 13684221.
6(2), s 373 399

Biørn, Erik (2003). Handling the Measurement Error Problem by Means of Panel Data: Moment Methods Applied on Firm Data, In Bernt Petter Stigum (ed.),
Econometrics and the Philosophy of Economics. TheoryData Confrontations in Economics.
Princeton University Press.
ISBN 0691113009.
24.
s 613
 641

Biørn, Erik; Lindquist, KjerstiGro & Skjerpen, Terje (2003). Random Coefficients in Unbalanced Panels: An Application on Data From Chemical Plants. Annales d'Èconomie et de Statistique.
ISSN 0769489X.
69, s 55 83
Vis sammendrag
A framework for analyzing substitution and scale properties from plantlevel panel data is presented. Focus is on comparing the constant and random coefficient specification of the substitution and scale parameters and investigating the variation of the parameters across plants. Characteristics of the model framework are (i) an equation system consisting of a threefactor translog cost function and the corresponding costshare equations, (ii) random plant specific heterogeneity in coefficients, and (iii) a Maximum Likelihood procedure allowing for unbalanced panel data. The empirical results, based on data from Norwegian chemical plants, indicate pronounced plant specific heterogeneity in substitution and scale properties. Substantial parts of the variances of the cost and the cost shares can be ascribed to variation in the coefficient vector. The estimated mean scale properties are considerably influenced by the choice of model specification, while conclusions regarding price effects are more robust.

Biørn, Erik; Hagen, Terje P.; Iversen, Tor & Magnussen, Jon (2003). The Effect of ActivityBased Financing on Hospital Efficiency: A Panel Data Analysis of DEA Efficiency Scores 19922000. Health Care Management Science.
ISSN 13869620.
6(4), s 271 283
Vis sammendrag
Activitybased financing (ABF) was implemented in the Norwegian hospital sector from 1 July 1997. A fraction of the block grants from the state to the county councils has been replaced by a matching grant depending upon the number and composition of hospital treatments. As a result of the reform, the majority of county councils have introduced activitybased contracts with their hospitals. This paper studies the effect of activitybased funding on hospital efficiency. We predict that hospital efficiency will increase because the benefit from costreducing efforts in terms of number of treated patients is increased under ABF as compared with global budgets. The prediction is tested using a panel data set from the period 19922000. Efficiency indicators are estimated by means of data envelopment analysis (DEA) with multiple inputs and outputs. Using a variety of econometrics methods, we find that the introduction of ABF has improved efficiency when measured as technical efficiency according to DEA analysis. The result is less unform with respect to the effect on costefficiency.

BrettevilleJensen, Anne Line & Biørn, Erik (2003). Heroin consumption, prices and addiction: Evidence from selfreported panel data. The Scandinavian Journal of Economics.
ISSN 03470520.
105(4), s 661 679 . doi:
10.1111/j.03470520.2003.00008.x
Vis sammendrag
Estimation models of drug demand should encompass the aspect of addiction. Here, we consider two static panel data regression models and two crosssection models with lags or leads in drug consumption as additional regressors. Heroin injectors attending a needle exchange service in Oslo were interviewed twice, with a one year interval. Despite our relatively small sample, we obtain statistically significant price and income responses for nearly all of the models and specifications applied. The sample is split by dealing status, with dealers obtaining price elasticities in the range of [0.15, 1.51] and nondealers [0.71, 1.69]. Somewhat surprisingly, the estimates of the variance of the latent individual specific variable are rather low in the panel data models, although higher for nondealers than for dealers.

Biørn, Erik; Lindquist, KjerstiGro & Skjerpen, Terje (2002). Heterogeneity in Returns to Scale: A Random Coefficient Analysis with Unbalanced Panel Data. Journal of Productivity Analysis.
ISSN 0895562X.
18(1), s 39 57
Vis sammendrag
This paper analyses the importance of scale economies by means of unbalanced plantlevel panel data from three Norwegian manufacturing industries. Focus is on heterogeneous technologies, and unlike most previous work on micro data, the model description includes heterogeneity in both the scale properties (the slope coefficients) and the intercept term, represented by random coefficients in the production function. Three (nested) functional forms are investigated: the Translog, an extended CobbDouglas, and the strict CobbDouglas. Although constant or moderately increasing returns to scale is found for the average plant, the results reveal considerable variation across plants. Variations in both input and scale elasticities are to a larger extent due to randomness of the production function parameters than to systematic differences in the input mix.

Biørn, Erik (2000). Panel Data with Measurement Errors: Instrumental Variables and GMM Procedures Combining Levels and Differences. Econometric Reviews.
ISSN 07474938.
19(4), s 391 424
Vis sammendrag
The estimation of linear, static regression equations from panel data with measurement errors in the regressors is considered. If the latent regressor is autocorrelated or nonstationary, several consistent instrumental variables (IV) and generalized method of moments (GMM) estimators usually exist, provided some structure is imposed on the disturbances and measurement errors. Applications of GMM procedures (i) on equations in differences with IV's in levels and (ii) on equations in levels with IV's in differences  the difference ransformations eliminating unobserved individual heterogeneity  are considered. The IV's may be constructed from values of the regressors or the regressand. Some of the orthogonality conditions delimiting the valid IV's are redundant. Illustrations based on data on inputs and outputs from an eight year panel of manufacturing firms are given.

Biørn, Erik & Klette, Tor Jakob (1999). The Labour Input Response to Permanent Changes in Output: An ErrorsinVariables Analysis Based on Panel Data. The Scandinavian Journal of Economics.
ISSN 03470520.
101, s 379 404
Vis sammendrag
Using panel data for Norwegian manufacturing, we revisit 'the increasing returns to scale puzzle' for labour inputs. We consider the response of the input of whitecollar workers, bluecollar workers, and bluecollar worker hours to permanent changes in output. Permanent and temporary changes in output are treated as latent variables. We compare OLS, IV, and GMM estimates of the response elasticities and conclude that the distinction between permanent and temporary changes is essential. Our GMM estimates suggest that the 'increasing returns to scale puzzle' remains for all measures of the labour input also when we consider their response to permanent changes in output. For materials, the output response indicates approximately constant returns to scale. This suggests nonhomotheticity of the production technology.

Biørn, Erik (1998). Survival and Efficiency Curves for Capital and the TimeAgeProfile of Vintage Prices. Empirical Economics.
ISSN 03777332.
23, s 611 633
Vis sammendrag
The decline in the service flow from a stock of capital goods with age, due to the physical retirement of capital units and to the gradual loss of efficiency of each unit remaining, can be described by survival curves and efficiency curves. The paper reconsiders the relationship between these curves and the vintage prices of capital under neoclassical assumptions about perfect second hand markets and malleability, using duality between quantites and prices. Three examples with parametric survival and efficiency curves are presented. Concavity of the survival and efficiency curves may be compatible with convexity of the ageprice profile. This approach is contrasted with the frequently cited HultenWykoff approach. Empirical illustrations, focusing on the cenvexity/concavity issue, are given.

Biørn, Erik; Golombek, Rolf & Raknerud, Arvid (1998). Environmental Regulations and Plant Exit: A Logit Analysis Based on Establishment Panel Data. Environmental and Resource Economics.
ISSN 09246460.
11, s 35 59
Vis sammendrag
A qualitative response model is applied to study the relationship between environmental regulations and plant exit. The data set is Norwegian panel data for establishments in three manufacturing sectors that have high shares of units which have been under strict environmental regulations. In two of the sectors, the estimated exit probability of regulated establishments is, cet. par., only one third of the exit probability of nonregulated establishments. We also find that the probability to change regulation status from being nonregulated to become regulated depends significantly on economic factors. In particular, establishments with weak profitability had the highest probability to become under environmental regulation.

Biørn, Erik & Klette, Tor Jakob (1998). Panel Data with ErrorsinVariables: Essential and Redundant Orthogonality Conditions in GMMEstimation. Economics Letters.
ISSN 01651765.
59(3), s 275 282
Vis sammendrag
General Method of Moments (GMM) estimation of a linear oneequation model using panel data with errorsinvariables is considered. To eliminate fixed individual heterogeneiety, the equation is differenced across one or more than one periods and estimated be means of instrumental variables. With nonautocorrelated measurement error, we show that only the oneperiod and a few of the twoperiod differences are essential, i.e. relevent for GMMestimation. GMM estimation based on all orthogonality conditions on the basis of a generalized inverse formulation is shown to be equivalent to estimation using only the essential orthogonality conditons.

Biørn, Erik (1996). Panel Data with Measurement Errors, In Laszlo Matyas & Patrick Sevestre (ed.),
The Econometrics of Panel Data. A Handbook of the Theory with Applications. Second Revised Edition.
Kluwer Academic Publishers.
ISBN 0792337875.
Chapter 10.
s 236
 279

Biørn, Erik (1994). Moment Estimators and the Estimation of Marginal Budget Shares from Household Panel Data. Structural Change and Economic Dynamics.
ISSN 0954349X.
5, s 133 154

Aasness, Jørgen; Biørn, Erik & Skjerpen, Terje (1993). Engel Functions, Panel Data, and Latent Variables. Econometrica.
ISSN 00129682.
61, s 1395 1422

Biørn, Erik (1992). Panel Data with Measurement Errors, In Laszlo Matyas & Patrick Sevestre (ed.),
The Econometrics of Panel Data. Handbook of Theory and Applications.
Kluwer Academic Publishers.
ISBN 0792320433.
Chapter 8.
s 152
 195

Biørn, Erik & Frenger, Petter (1992). Expectations, Substitution, and Scrapping in a PuttyClay Model. Journal of Economics.
ISSN 09318658.
56, s 157 184

Biørn, Erik & Olsen, Hilde (1989). ProductionDemand Adjustment in Norwegian Manufacturing. A Quarterly Error Correction Model. Economic Modelling.
ISSN 02649993.
6, s 189 202

Biørn, Erik (1988). Bedriftsbeskatning og kapitalomkostninger  en oversikt. Norsk Økonomisk Tidsskrift.
ISSN 08019568.
102, s 31 59

Biørn, Erik; Jensen, Morten & Reymert, Morten (1987). KVARTS A Quarterly Model of the Norwegian Economy. Economic Modelling.
ISSN 02649993.
4, s 77 109

Biørn, Erik; Jensen, Morten & Knudsen, Vidar (1985). Korttidsdynamikk i norsk økonomi belyst ved kvartalsmodellen KVARTS. Sosialøkonomen.
ISSN 00381624.
39(56), s 20/26 29/33

Biørn, Erik & Jansen, Eilev S. (1983). Individual Effects in a System of Demand Functions. The Scandinavian Journal of Economics.
ISSN 03470520.
85, s 461 483

Biørn, Erik (1981). Estimating Economics Relations from Incomplete CrossSection/TimeSeries Data. Journal of Econometrics.
ISSN 03044076.
16, s 222 236

Biørn, Erik (1980). The Consumption Function and the Life Cycle Hypothesis: An Analysis of Norwegian Household Data. The Scandinavian Journal of Economics.
ISSN 03470520.
82, s 464 480

Biørn, Erik (1975). The Distributive Effects of Indirect Taxation: An Econometric Model and Empirical Results Based on Norwegian Data. Swedish Journal of Economics.
77, s 1 12

Biørn, Erik (1974). Estimating the Flexibility of the Marginal Utility of Money. European Economic Review.
ISSN 00142921.
5, s 177 185

Biørn, Erik (1971). Fordelingsvirkninger av indirekte skatter og subsidier. Norsk Økonomisk Tidsskrift.
ISSN 08019568.
85, s 1 31
Se alle arbeider i Cristin

Biørn, Erik (2016). Econometrics of Panel Data: Methods and Applications.
Oxford University Press.
ISBN 9780198753445.
416 s.

Biørn, Erik (2009). Økonometriske emner. 3. utgave.
Unipub forlag.
ISBN 9788274773998.
370 s.

Biørn, Erik (2008). Økonometriske emner. En videreføring.
Unipub forlag.
ISBN 9788274773592.
326 s.

Biørn, Erik (2003). Økonometriske emner, 2. utgave.
Unipub forlag.
ISBN 8274771524.
386 s.

Biørn, Erik (2000). Økonometriske emner.
Unipub forlag.
ISBN 8274770544.
419 s.
Vis sammendrag
Økonometri er et fagområde i grenselandet mellom økonomi, særlig samfunnsøkonomi, og statistikk. En av økonometriens hovedoppgaver er å tallfeste økonomiske relasjoner, teorier og modeller og å undersøke holdbarheten av dem ved hjelp av statistiske metoder. Denne boken er primært tenkt som en lærebok for et relativt elementært kurs i økonometri. Den kan også brukes som grunnlag for selvstudium for lesere som ønsker en innføring i faget. Fremstillingen inneholder en blanding av teori og anvendelser på samfunnsøkonomiske problemstillinger. I bokens første del diskuteres utvalgte emner fra klassisk regresjonsanalyse anvendt på ikkeeksperimentelle data. Anvendelser av systemer av regresjonsligninger til analyse av konsumenters og bedrifters økonomiske adferd, behandles dernest. Identifikasjonsproblemet, som er et basalt problem ved konfrontasjon av teorimodeller med ikkeeksperimentelle data, diskuteres. I bokens annen del behandles økonometriske metoder knyttet til simultane ligningssystemer hvor flere variable står i gjensidig avhengighet, og problemer og metoder relatert til analyse av data med målefeil.

Biørn, Erik (1989). Taxation, Technology and the User Cost of Capital.
North Holland.
ISBN 0444874909.
325 s.

Biørn, Erik & Jansen, Eilev S. (1982). Econometrics of Incomplete CrossSection/Time Series Data: Consumer Demand in Norwegian Households 19751977.
Statistisk sentralbyrå.
ISBN 8253717822.
307 s.

Biørn, Erik (1980). Analyse av sammenhengen mellom forbruk, inntekt og formue i norske husholdninger.
Statistisk sentralbyrå.
ISBN 8253710127.
95 s.

Biørn, Erik (1979). Analyse av investeringsatferd. Problemer, metoder og resultater.
Statistisk sentralbyrå.
ISBN 8253709528.
91 s.

Biørn, Erik & Garaas, Erik (1976). Inntekts og forbruksbeskatning fra et fordelingssynspunkt en modell for empirisk analyse.
Statistisk sentralbyrå.
ISBN 8253706472.
148 s.
Se alle arbeider i Cristin

Biørn, Erik (2017). Identification and Method of Moments Estimation in Polynomial Measurement Error Models. Memorandum from Department of Economics, University of Oslo. 01/2017.
Vis sammendrag
Estimation of polynomial regression equations in one errorridden variable and a number of errorfree regressors, as well as an instrument set for the former is considered. Procedures for identification, operating on moments up to a certain order, are elaborated for single and multiequation models. Weak distributional assumptions are made for the error and the latent regressor. Simple orderconditions are derived, and procedures involving recursive identification of the moments of the regressor and its measurement errors together with the coefficients of the polynomials are considered. A Generalized Method of Moments (GMM) algorithm involving the instruments and proceeding stepwise from the identification procedures, is presented. An illustration for systems of linear, quadratic and cubic Engel functions, with household consumption and income data is given.

Biørn, Erik (2017). Identification, Instruments, Omitted Variables, and Rudimentary Models: Fallacies in the `Experimental Approach' to Econometrics. Memorandum from Department of Economics, University of Oslo. 13/2017.
Vis sammendrag
Since identification, instrumental variables and variables exclusion, core concepts in econometrics, are entwined, several questions arise: How is identification related to the existence of IVs? How are identification criteria related to omitted variables? Is omission/inclusion of variables from a model's equations part of the definition of IVs? Is exogeneity a critical claim to an IV? Is `omitted variables' a meaningful term for a single equation when its `environment' is incompletely described? Which are the borderlines between omitted, observable variables, omitted nonmodeled variables, latent variables represented by proxies or measurement error mechanisms? These are among the questions addressed in this paper, partly with reference to the conflict between `experimentalists' and `structuralists', specifically relating to: (i) the contrast between `rudimentary models' and models for `limited information inference', (ii) the distinction between exogeneity of variables and the orthogonality claim for IVs and disturbances or errors, (iii) the role of predetermined variables in selecting IVs, and (iv) the `omitted variables' concept and the role of IVs in `handling' such variables, when considering the `origin' of the omission.

Biørn, Erik (2017). Kurs i paneldataøkonometri. Del 1: Generelt. Regresjonsanalyse med paneldata .

Biørn, Erik (2017). Kurs i paneldataøkonometri. Del 2: Regresjonsanalyse. Videreføring..

Biørn, Erik (2017). Kurs i paneldataøkonometri: Del 3: Dynamiske modeller. Ubalanserte paneler etc..

Biørn, Erik (2017). Kurs i paneldataøkonometri: Del 4: Stokastiske koeffisienter. Målefeilmodeller. Flerligningsmodeller.

Biørn, Erik (2017). Revisiting, from a Frischian Point of View, the Relationship Between Elasticities of Intratemporal and Intertemporal Substitution. Memorandum from Department of Economics, University of Oslo. 04/2017.
Vis sammendrag
How are substitution in the spatial and in the temporal sense connected? Can estimates based on data with spatial variation be transmitted into values appropriate for exploring temporal variation, and vice versa? This paper, building on, inter alia, Frisch (1959), attempts to give some clariﬁcations and provides elements of a synthesis. The income elasticity of the marginal utility of income, whose inverse is often called the ‘Frisch parameter’, and its multiperiod counterpart, the wealth elasticity of the marginal utility of wealth, are key concepts. Three cases with additive preferences are discussed, and in that context the role of the (generalized) ‘Frisch parameter’ as an overall measure of substitution across commodities and over time is reconsidered.

Biørn, Erik (2016). Panel Data Estimators and Aggregation. Memorandum from Department of Economics, University of Oslo. 19/2016.
Vis sammendrag
For a panel data regression equation with twoway unobserved heterogeneity, individualspecific and periodspecific, ‘withinindividual’ and ‘withinperiod’ estimators, which can be given Ordinary Least Squares (OLS) or Instrumental Variables (IV) interpretations, are considered. A class of estimators defined as linear aggregates of these estimators, is defined. Nine aggregate estimators, including between, within, and Generalized Least Squares (GLS), are special cases. Other estimators are shown to be more robust to simultaneity and measurement error bias than the standard aggregate estimators and more efficient than the ‘disaggregate’ estimators. Empirical illustrations relating to manufacturing productivity are given.

Biørn, Erik & Han, Xuehui (2015). Persistence, SignalNoise Pattern and Heterogeneity in Panel Data: With an Application to the Impact of Foreign Direct investment on GDP. Memorandum from Department of Economics, University of Oslo. 4/2015.
Vis sammendrag
GMM estimation of autoregressive panel data equations in errorridden variables when the noise has memory, is considered. The impact of variation in the memory length in signal and noise spread and in the degree of individual heterogeneity are discussed with respect to finite sample bias, using Monte Carlo simulations. Also explored are also the impact of the strength of autocorrelation and the size of the IV set. GMM procedures using IVs in differences on equations in levels, in general perform better in small samples than procedures using IVs in levels on equations in differences. A casestudy of the impact of Foreign Direct Investment (FDI) on GDP, \textit{inter alia}, contrasting the manufacturing and the service sector, based on country panel data supplements the simulation results.

Biørn, Erik (2014). Econometric Approaches to Market Models for Capital and Investment.

Biørn, Erik (2014). Serially Correlated Measurement Errors in Time Series Regression: The Potential of Instrumental Variable Estimators. Memorandum from Department of Economics, University of Oslo. 28/2014.
Vis sammendrag
The measurement error problem in linear time series regression, with focus on the impact of error memory, modeled as finiteorder MA processes, is considered. Three prototype models, two bivariate and one univariate ARMA, and ways of handling the problem by using instrumental variables (IVs) are discussed as examples. One has a bivariate regression equation that is static, although with dynamics, entering via the memory of its latent variables. The examples illustrate how `structural dynamics' interacting with measurement error memory create bias in Ordinary Least Squares (OLS) and illustrate the potential of IV estimation procedures. Supplementary Monte Carlo simulations are provided for two of the example models.

Biørn, Erik (2014). The PriceQuantity Decomposition of Capital Values Revisited: Framework and Examples. Memorandum from Department of Economics, University of Oslo. 27/2014.
Vis sammendrag
The often discussed problems of aggregating tangible capital assets across vintages and of decomposing value aggregates into quantity and price aggregates are revisited. For stock values and service flow values, some new results are given, and illustrated by examples, along with reinterpretations of familiar ones. If the definitions and measurement methods for prices and quantities do not `match', a third, `quality', component may be needed. Should this `buffer' component be included in the price or quantity components, or both, or should it be accounted for separately, and in the latter case, how does it depend on the interest rate and the capital's age? In discussing these issues, five related quantity variables and five related price variables are introduced and discussed. For certain parametric profiles for survival and efficiency loss they are equal. Some variables are observable from market data without large efforts, some are genuinely unobservable, and some can be quantified only if certain (sometimes questionable and often nontestable) assumptions are made. Examples based on three sets of parametric profiles, including exponential decay, are given.

Biørn, Erik (2013). AgeCohortTime Effects in Sickness Absence: Exploring a Large Data Set by Polynomial Regression. Memorandum from Department of Economics, University of Oslo. 19/2013.
Vis sammendrag
Identification of equations explaining a continuous variable, e.g., the length of sickness absence spells, by age, cohort and time (ACT), subject to their definitional identity is reconsidered. Various extensions of a linear equation to polynomials are explored. If no interactions between the ACT variables are included, only the coefficients of the linear terms create identification problems. A data set with 4.5 million individual observations for longterm sickness absence in Norway is used. The sensitivity of the estimated marginal effects of cohort and age on the length of the absence spells, at the sample mean, is illustrated. Notable differences are found between linear and quadratic equations on the one hand and cubic and fourthorder polynomials on the other. Representing heterogeneity by cohort effects is compared with representing heterogeneity by random and fixed individual effects. On the whole, the age coefficients in the estimated regressions are quite sensitive to how heterogeneity is modeled.

Biørn, Erik (2013). Identifying AgeCohortTime Effects, Their Curvature and Interactions from Polynomials: Examples Related to Sickness Absence. Memorandum from Department of Economics, University of Oslo. 08/2013.
Vis sammendrag
In the paper is considered identification of coefficients in equations explaining a continuous variable, say the number of sickness absence days of an individual per year, by cohort, time and age, subject to their definitional identity. Extensions of a linear equation to polynomials, including additive polynomials, are explored. The cohort+time=age identity makes the treatment of interactions important. If no interactions between the three variables are included, only the coefficients of the linear terms remain unidentified unless additional information is available. Illustrations using a large data set for individual longterm sickness absence in Norway are given. The sensitivity to the estimated marginal effects of cohort and age at the samplemean, as well as conclusions about the equations’ curvature, are illustrated. We find notable differences in this respect between linear and quadratic equations on the one hand and cubic and fourthorder polynomials on the other.

Biørn, Erik & Bjørnsen, Marte (2013). What Motivates Farm Couples to Seek OffFarm Labour? A Logit Analysis of Job Transitions.

Biørn, Erik & Bjørnsen, Marte (2013). What Motivates Farm Couples to Seek Offfarm Labour? A Logit Analysis of Job Transitions. Memorandum from Department of Economics, University of Oslo. 09/2013.
Vis sammendrag
In this paper some labour market consequences of transitions in the agriculture sector are examined by combining a 20year unbalanced panel data set from Norwegian farm couples (households) and logit modeling of oneperiod transition probabilities. The multidimensionality of the problem follows from two decision makers (partners) having four possible choices in each period: the farm operator and spouse can be working fully on the farm or having supplementary outside occupation. Transition probabilities are modeled by five alternative logit models. State dependence is represented to different extent. The most flexible model has a high number of parameters. Overall, the results indicate that transitions have mainly bee directed towards the state where both partners work off the farm. An increasing livestock reduces the probability of moving to states with substantial offfarm labour participation. Increased farm size tends to have the opposite effect. Recent onfarm investments come out with ambiguous effects, and the pattern seems to change during the observation period. Having children seems to motivate operators to withdraw from offfarm labour and spouses to stay in or entering offfarm employment.

Biørn, Erik & Han, Xuehui (2013). Panel Data Models With Dynamics and Measurement Error: GMM Performance when Autoregression and Error Memory Interact  Some Small Sample Evidence.

Biørn, Erik (2012). An Econometric Market Model of Capital and Investment Inspired by Haavelmo. Memorandum from Department of Economics, University of Oslo. 11/2012.
Vis sammendrag
In the paper steps are taken towards integration of two parts of Trygve Haavelmo’s work: investment theory and econometrics of interrelated markets. Attempts are made to bring the duality in the representation of the capital service price and the capital quantity in relation to the investment price and quantity into the foreground, by confronting it with elements from simultaneous equation modeling of vector autoregressive systems with exogenous variables (VARX), using linear fourequation models. The role of the interest rate and the modeling of the expectation element in the capital service price and the capital’s retirement pattern, and their joint effect on the model’s investment quantity and price dynamics are discussed. Simulation experiments illustrate some of the theoretical points. An extension relaxing geometric decay is outlined.

Biørn, Erik (2012). Estimating SUR Systems with Random Coefficients: The Unbalanced Panel Data Case. Memorandum from Department of Economics, University of Oslo. 22/2012.
Vis sammendrag
A system of regression equations (SURE) for analyzing panel data with random heterogeneity in intercepts and coefficients, and unbalanced panel data is considered. A Maximum Likelihood (ML) procedure for joint estimation of all parameters is described. Since its implementation for numerical computation is complicated, simplified procedures are presented. The simplifications essentially concern the estimation of the covariance matrices of the random coefficients. The application and `anatomy' of the proposed algorithm for modified ML estimation is illustrated by using panel data for output, inputs and costs for 111 manufacturing firms observed up to 22 years.

Biørn, Erik (2012). The Measurement Error Problem in Dynamic Panel Data Analysis: Modeling and GMM Estimation. Memorandum from Department of Economics, University of Oslo. 02/2012.
Vis sammendrag
The Generalized Method of Moments (GMM) is discussed for handling the joint occurrence of fixed effects and random measurement errors in an autoregressive panel data model. Finite memory of disturbances, latent regressors and measurement errors is assumed. Two specializations of GMM are considered: (i) using instruments (IVs) in levels for a differenced version of the equation, (ii) using IVs in differences for an equation in levels. Index sets for lags and lags are convenient in examining how the potential IV set, satisfying orthogonality and rank conditions, changes when the memory pattern changes. The joint occurrence of measurement errors with long memory may sometimes give an IVset too small to make estimation possible. On the other hand, problems of ‘IV proliferation’ and ‘weak IVs’ may arise unless the timeseries length is small. An application based on data for (logtransformed) capital stock and output from Norwegian manufacturing firms is discussed. Finite sample biases and IV quality are illustrated by Monte Carlo simulations. Overall, with respect to bias and IV strength, GMM inference using the level version of the equation seems superior to inference based on the equation in differences.

Biørn, Erik & Han, Xuehui (2012). Panel Data Dynamics and Measurement Errors: GMM Bias, IV Validity and Model Fit  A Monte Carlo Study. Memorandum from Department of Economics, University of Oslo. 27/2012.
Vis sammendrag
An autoregressive fixed effects panel data equation in errorridden endogenous and exogenous variables, with finite memory of disturbances, latent regressors and measurement errors is considered. Finite sample properties of GMM estimators are explored by Monte Carlo (MC) simulations. Two kinds of estimators are compared with respect to bias, instrument (IV) validity and model fit: equation in differences/IVs levels, equation in levels/IVs in differences. We discuss the impact on estimators' bias and other properties of their distributions of changes in the signalnoise variance ratio, the length of the signal and noise memory, the strength of autocorrelation, the size of the IV set, and the panel length. Finally, some practical guidelines are provided.

Biørn, Erik & Wangen, Knut Reidar (2012). New Taxonomies for Limited Dependent Variables Models. MPRA Paper. 41461.
Vis sammendrag
We establish a `map' for describing a wide class of Limited Dependent Variables models much used in the econometric literature. The classification system, or language, is an extension of Amemiya's typology for tobit models and is intended to facilitate communication among researchers. The class is defined in relation to distributions of latent variables of an arbitrarily high dimension; the region of support can be divided into an arbitrary number of subsets, and the observation rules in each subset can be any combination of the observed, censored, and missing status. Consistent labeling is suggested at different levels of detail.

Biørn, Erik (2011). An Econometric Market Model of Capital and Investment.

Biørn, Erik (2011). Doing Econometrics with Panel Data: Advantages and Selected Approaches.

Biørn, Erik & Wangen, Knut Reidar (2011). Models of Truncation, Sample Selection, and Limited Dependent Variables: Suggestions for a Common Language. Memorandum from Department of Economics, University of Oslo. 18/2011.
Vis sammendrag
The aim of this paper is twofold: (a) to establish a ‘map’ for describing the wide class of Limited Dependent Variables (LDV) univariate and multivariate models in the econometric literature and (b) to localize typical models in this tradition within the structure, extending typologies of Heckman (1976) and Amemiya (1984). The classification system, or language, proposed, is given at different level of detail. Its scope is (1) that the latent variables can have any parametric distribution, (2) that a set of observation rules which include the observed, censored, missing status, is imposed, (3) that it should be possible to write a model combining (1) and (2) by means of a computer algorithm, also potentially applicable for generating samples and (4) that the models belonging to the system should have names to facilitate communication among researchers. The likelihood functions corresponding to the models’ observed endogenous variables are discussed, but the paper is not concerned with describing the application of these functions for inference.

BrettevilleJensen, Anne Line; Biørn, Erik & Selmer, Randi (2011). Quitting Behaviour of Cigarette Smokers. Are There Direct Effects of a Screening Program?. Memorandum from Department of Economics, University of Oslo. 07/2011.
Vis sammendrag
This paper aims at i) providing effect estimates of a wide range of covariates and traditional policy means to increase the smoking cessation rate, ii) offering evidence on alternative interventions for health authorities, and iii) examining and comparing three groups of smokers with varying lengths of their smoking career (including one group that has smoked ≥ 25 years). All smokers have been subject to a threewave cardiovascular screening and followed up over a maximum of 14 years. This rich panel data set has been merged with administrative registers. A flexible discretetime duration model is used to examine the effect of 5 categories of explanatory variables: personal characteristics; indicators of addiction status; economic factors; health and health shock variables; governmental interventions. Most covariates differ across groups, but for all groups did the screening participation years stand out as important. Possible policy implications for future cessation interventions are discussed.

Biørn, Erik (2010). Identifying Trend and Age Effects in Sickness Absence from Individual Data: Some Econometric Problems. Memorandum from Department of Economics, University of Oslo. 20/2010.
Vis sammendrag
When using data from individuals who are in the labour force to disentangle the empirical relevance of cohort, age and time effects for sickness absence, the inference may be biased, affected by sortingout mechanisms. One reason is unobserved heterogeneity potentially affecting both health status and ability to work, which can bias inference because the individuals entering the data set are conditional on being in the labour force. Can this sample selection be adequately handled by attaching unobserved heterogeneity to nonstructured fixed effects? In the paper we examine this issue and discuss the econometric setup for identifying from such data time effects in sickness absence. The inference and interpretation problem is caused, on the one hand, by the occurrence of time, cohort and age effects also in the labour market participation, on the other hand by correlation between unobserved heterogeneity in health status and in ability to work. We show that running panel data regressions, ordinary or logistic, of sickness absence data on certain covariates, when neglecting this sample selection, is likely to obscure the interpretation of the results, except in certain, not particularly realistic, cases. However, the fixed individual effects approach is more robust in this respect than an approach controlling for fixed cohort effects only.

Biørn, Erik (2010). Kurs i paneldataøkonometri. Del 1: Generelt. Regresjonsanalyse med paneldata.

Biørn, Erik (2010). Kurs i paneldataøkonometri. Del 2: Regresjonsanalyse: Videregående emner.

Biørn, Erik (2010). Kurs i paneldataøkonometri: Del 3: Dynamiske modeller.

Biørn, Erik (2010). Kurs i paneldataøkonometri: Del 4: Ubalanserte paneler og flerligningsmodeller.

Biørn, Erik (2010). Regression Systems with Random Coefficients: Estimation Procedures for the Unbalanced Panel Data Case.

Biørn, Erik & Bjørnsen, HildMarte (2010). Farm Couples' OffFarm Choice of Labour Supply: A Panel Data Analysis of Job Transitions.

Biørn, Erik; Gaure, Simen; Markussen, Simen & Røed, Knut (2010). The Rise in Absenteeism: Disentangling the Impacts of Cohort, Age and Time. IZA DP. 5091.
Vis sammendrag
We examine the remarkable rise in absenteeism among Norwegian employees since the early 1990’s, with particular emphasis on disentangling the roles of cohort, age, and time. Based on a fixed effects model, we show that individual ageadjusted absence propensities have risen even more than aggregate absence rates from 1993 to 2005, debunking the popular hypothesis that the rise in absenteeism resulted from the inclusion of new cohorts – with weaker worknorms – into the workforce. We also reject the idea that the rise in absenteeism resulted from more successful integration of workers with poor health; on the contrary, a massive rise in disability rolls during the 1990’s

BrettevilleJensen, Anne Line; Biørn, Erik & Selmer, Randi (2009). Quitting Behaviour of cigarette smokers  Are there direct effects of a screening program?.

Biørn, Erik (2009). Capital Decay and Tax Distortions: How to Abandon Exponential Decay and Benefit from It. Memorandum from Department of Economics, University of Oslo. 27/2009.
Vis sammendrag
The appropriate way of quantifying how taxation of a firm's income and capital can distort its optimizing conditions is a recurring issue in the literature on optimal taxation. Exponential decay, although empirically contested, is almost ubiquitous. In the present paper a generalized framework which allows for a general, nonexponential, decay pattern for both true and taxpermitted depreciation, is considered. Both convex and concave survival functions can be accommodated. Three capital concepts are involved, two of which coincide under exponential decay. The tradeoff between various departures from neutrality is illustrated. Elements which contribute to nonneutrality are: (i) discrepancy between the definition of the taxrelevant accounting capital and true depreciation, (ii) misindexation of depreciation allowances, (iii) incomplete deductibility of interest costs, (iv) asymmetric treatment of interest costs and capital gains, and (v) taxation of the value of the capital stock. Finally, we show that substantial biases can arise in assessing the degree of nonneutrality if nonexponential depreciation schedules are forced, by `approximation devices', to fit into the exponential decay schedule.

Biørn, Erik (2009). Econometric Analysis of Panel Data  An Introduction.

Biørn, Erik (2009). Measurement Errors in Dynamic Panel Data Analysis: A Synthesis on Modelling and GMM Estimation.

Biørn, Erik (2009). Measurement Errors in Dynamic Panel Data Analysis: A Synthesis on Modelling and GMM Estimation.

Biørn, Erik (2009). Measurement Errors in Dynamic Panel Data Analysis: A Synthesis on Modelling and GMM Estimation.

Biørn, Erik (2009). Modelling Addiction in LifeCycle Models: Revisiting the Treatment of Latent Stocks and Other Unobservables. Memorandum from Department of Economics, University of Oslo. 26/2009.
Vis sammendrag
Dynamic modeling of demand for goods whose cumulated stocks enter an intertemporal utility function as latent variables, is discussed. The issues include: how represent addiction, how handle unobserved expectations and changing plans, how deal with `dynamic inconsistency'? Arguments are put forth to give all optimizing conditions attention, not only those in which all variables are observable. If the latter, fairly common, `limited informationreduced dimension' strategy is pursued, problems are shown to arise in attempting to identify coefficients of the preference structure and to test for addictive stocks. Examples, based on quadratic utility functions, illustrate the main points and challenge the validity of testing the `rational addiction' hypothesis, by using linear, singleequation autoregressive models, as suggested by Becker, Grossman, and Murphy (1994) and adopted in several following studies.

Biørn, Erik; Gaure, Simen; Markussen, Simen & Røed, Knut (2009). The rise of absenteeism in Norway: Disentangling the impacts of cohort, age and time.

Biørn, Erik & Wangen, Knut Reidar (2009). Limited Dependent Variables Models: Reconsidering the Typology and a Suggested Synthesis.

Biørn, Erik (2008). Measurement Errors in Dynamic Panel Data Analysis: A Synthesis on Modelling and GMM Estimation.

Biørn, Erik (2008). Measurement Errors in Dynamic Panel Data Analysis: A Synthesis on Modelling and GMM Estimation.

Biørn, Erik & Godager, Geir (2008). Does Quality Influence Choice of General Practitioner? An Analysis of Matched Doctor Patient Panel Data.

Biørn, Erik & Godager, Geir (2008). Does quality influence choice of general practitioner? An analysis of matched doctorpatient panel data. HERO skriftserie / Working paper. 3.
Vis sammendrag
The impact of quality on the demand facing health care providers has important implications for the industrial organization of health care markets. In this paper we study the consumers' choice of general practitioner (GP) assuming they are unable to observe the true quality of GP services. A panel data set for 484 Norwegian GPs, with summary information on their patient stocks, renders the opportunity to identify and measure the impact of GP quality on the demand, accounting for patient health heterogeneity in several ways. We apply modeling and estimation procedures involving latent structural variables, inter alia, a LISREL type of model, is used. The patient excess mortality rate at the GP level is one indicator of the quality. We estimate the effect of this quality variable on the demand for each GP's services. Our results, obtained from two different econometric model versions, indicate that GP quality has a clear positive effect on demand.

Biørn, Erik (2007). Latent Stocks in Econometric Implementations of Lifecycle Theories, Exemplified by Addiction.

Biørn, Erik (2007). Measuring and Decomposing Capital Stock and Service Values: Should Capital Quality be Given a Place?. Discussion Papers. 518.
Vis sammendrag
Aggregation of tangible capital assets across vintages and decomposition of value aggregates into quantities and prices are considered. Focus is on both capital stock values and capital service values. If the definitions and ways of measuring prices and quantities are not conformable, a third component, denoted a quality component, may have to be included as a buffer. Should it then be suppressed by allocating it to either of the price and quantity components, or should quality be accounted for separately? In discussing these issues, five quantity variables and five price variables are involved. Some of them are observable from market data without large efforts, some are essentially unobservable, and some can be quantified only if certain (often nontestable) assumptions are made. Illustrations based on parametric functions are given.

Biørn, Erik & Godager, Geir (2007). GP Quality, Imperfect Information and the Demand for GP Service: an Analysis of Matched DoctorPatient Panel Data.

Biørn, Erik; Hagen, Terje P.; Iversen, Tor & Magnussen, Jon (2007). Heterogeneity in Hospitals' Response to a Financial Reform: a Random Coefficient Analysis of the Impact of Activity Based Financing on Efficiency in Norway.

Biørn, Erik (2006). Identification and Method of Moment Estimation in Polynomial Mesurement Error Models.

Biørn, Erik; Hagen, Terje P.; Iversen, Tor & Magnussen, Jon (2006). Heterogeneity in Hospitals' Responses to a Financial Reform: A Random Coefficient Analysis of the Impact of ActivityBased Financing on Efficiency.

Biørn, Erik; Hagen, Terje P.; Iversen, Tor & Magnussen, Jon (2006). Heterogeneity in Hospitals' Responses to a Financial Reform: A Random Coefficient Analysis of the Impact of ActivityBased Financing on Efficiency.

Bjørnsen, HildMarte & Biørn, Erik (2006). The Joint Labour Decisions of Farm Couples: A Censored Response Analysis of Onfarm and Offarm Work.

Bjørnsen, HildMarte & Biørn, Erik (2006). The Joint Labour Decisions of Farm Couples: A Censored Response Analysis of Onfarm and Offfarm Work. Memorandum / Økonomisk institutt, UiO. 05/2006.
Vis sammendrag
Farm couples' labour market responses are partly the qualitative choice of entering the offfarm labour market and partly the continuous choice of the number of onfarm and offfarm working hours, given entry. Such a setting is interesting when examining the increasing occurrence of multiple jobholdings among farmers in western economies. This paper presents a unified framework for handling such discrete/continuous choices, involving optimisation of farm production, household consumption, and multiple jobholdings for both husband and wife. A twoequation censoring panel data model is implemented and estimated from Norwegian panel data for 342 farms observed over a tenyear period.

Biørn, Erik; Hagen, Terje P.; Iversen, Tor & Magnussen, Jon (2006). Heterogeneity in Hospitals' Responses to a Financial Reform: A Random Coefficient Analysis of The Impact of ActivityBased Financing on Efficiency. HERO skriftserie / Working paper. 9.
Vis sammendrag
The paper examines the heterogeneity with respect to the impact of a financial reform  Activity Based Financing (ABF)  on hospital efficiency in Norway. Measures of technical efficiency and of costefficiency are considered. The data set is from a contiguous tenyear panel of 47~hospitals covering both preABF years and years after its imposition. Substantial heterogeneity in the responses, as measured by both estimated and predicted coefficients, is found. Rank correlations between the estimated/predicted coefficients of the ABF dummy and the preABF/postABF efficiencies are examined. Overall, improvement seems to be more pronounced in technical efficiency than in costefficiency.

Biørn, Erik; Iversen, Tor; Hagen, Terje P. & Magnussen, Jon (2006). Heterogeneity in hospitals' responses to a financial reform. HERO skriftserie / Working paper. 9.

Biørn, Erik (2005). Addictive Stocks in Econometric Implementations of LifeCycle Theories.

Biørn, Erik (2005). Constructing Panel Data Estimators by Aggregation: A General Moment Estimator and a Suggested Synthesis.

Biørn, Erik (2005). Constructing Panel Data Estimators by Aggregation: A General Moment Estimator and a Suggested Synthesis.
Vis sammendrag
A regression equation for panel data with twoway random or fixed effects and a set of individual specific and period specific `within individual' and `within period', estimators of its slope coefficients are considered. They can be given Ordinary Least Squares (OLS) or Instrumental Variables (IV) interpretations. A class of estimators, obtained as an arbitrary linear combination of these `disaggregate' estimators, is defined and an expression for its variancecovariance matrix is derived. Nine familiar `aggregate' estimators which utilize the entire data set, including two between, three within, three GLS, as well as the standard OLS, emerge by specific choices of the weights. Other estimators in this class which are more robust to simultaneity and measurement error bias than the standard aggregate estimators and more efficient than the `disaggregate' estimators, are also considered. An empirical illustration of robustness and efficiency, relating to manufacturing productivity, is given.}

Biørn, Erik (2005). Econometric Analysis of Panel Data. An Introduction. Part 1: Basic Topics. Part 2: Advanced Topics.

Biørn, Erik (2005). Måling av kapitalverdier og deres pris og kvantumskomponenter. Trengs også en kvalitetskomponent?.

Biørn, Erik (2004). Polynomial Measurement Error Models for CrossSection and Panel Data: Identification and Method of Moments Estimation.

Biørn, Erik (2004). Polynomial Measurement Error Models for CrossSection and Panel Data: Identification and Method of Moments Estimation.

Biørn, Erik (2004). Polynommodeller for tverrsnitts og paneldata med målefeil. Identifikasjon og estimering ved momentmetoder.

Biørn, Erik; Skjerpen, Terje & Wangen, Knut R. (2004). Can Random Coefficient CobbDouglas Production Functions be Aggregated to Similar Macro Functions?.

Biørn, Erik; Skjerpen, Terje & Wangen, Knut R. (2004). Can Random Coefficient CobbDouglas Production Functions be Aggregated to Similar Macro Functions?. Memorandum / Økonomisk institutt, UiO. 22/2004.
Vis sammendrag
Parametric aggregation of heterogeneous micro production technologies is discussed. A fourfactor CobbDouglas function with normally distributed firm specific coefficients and with lognormal inputs (which agrees well with the available data) is specified. Since, if the number of micro units is large enough, aggregates expressed as arithmetic means can be associated with expectations, we consider conditions ensuring an approximate relation of CobbDouglas form to exist between expected output and expected inputs. Similar relations in higherorder moments are also derived. It is shown how the aggregate input elasticities depend on the coefficient heterogeneity and the covariance matrix of the loginput vector and hence vary over time. An implementation based on firm panel data for two manufacturing industries gives estimates of industry level input elasticities and decomposition for expected output. Finally, aggregation errors which emerge when the correct aggregate elasticities are replaced by the expected micro elasticities, are explored.

Biørn, Erik; Skjerpen, Terje & Wangen, Knut R. (2004). Can Random Coefficient CobbDouglas Production Functions be Aggregated to Similar Macro Functions?.

Aasness, Jørgen; Biørn, Erik & Skjerpen, Terje (2003). Supplement to "Distribution of Preferences and Measurement Errors in a Disaggregated Expenditure System". Documents  Statistisk sentralbyrå/Statistics Norway. 3.

Biørn, Erik (2003). Aggregeringsmetoder eksemplifisert ved produktfunksjoner.

Biørn, Erik (2003). Den generaliserte momentmetode (GMM)  en innføring.

Biørn, Erik; Skjerpen, Terje & Wangen, Knut Reidar (2003). Parametric Aggregation of Random Coefficient CobbDouglas Production Functions: Evidence from Manufacturing Industries.
Vis sammendrag
A panel data study of parametric aggregation of a production function is presented. A fourfactor CobbDouglas function with random and jointly normal coefficients and jointly lognormal inputs is used. Since, if the number of micro units is not too small and certain regularity conditions are met, aggregates expressed as arithmetic means can be associated with expectations, we consider conditions ensuring the existence and stability of relationships between expected inputs and expected output and discuss their properties. Existence conditions for and relationships between higherorder moments are considered. An empirical implementation based on panel data for two manufacturing industries gives decomposition and simulation results for expected output and estimates of the aggregate parameters. Illustrations of approximation procedures and aggregation errors are also given.

Biørn, Erik (2002). Handling the Measurement Error Problem by Means of Panel Data: Moment Methods Applied on Firm Data.

Biørn, Erik (2002). Handling the Measurement Error Problem by Means of Panel Data: Moment Methods Applied on Firm Data.

BrettevilleJensen, Anne Line & Biørn, Erik (2002). Drug Injection, Drug Dealing, and the Influence of Economic Factors: A TwoDrug MicroEconometric AnalDysis. DUPI working papers. 11.
Vis sammendrag
An important question for policy makers is how drug users may respond to changes in economic factors. Based on a unique data set of almost 2,500 interviews with people attending a needle exchange service in Oslo, this paper aims at estimating the impact of economic factors on heroin and amphetamine injectors' drug consumption. Four econometric models versions are considered. The results include, in addition to estimates of price and income elasticities within switching regression models treating dealing/nondealing as an endogenous decision, estimates of crossprice elasticities of the two drugs, and an examination of possible `kinks' in the demand curve of heroin. One dynamic model version specifically aims at examining the issue of addiction. Lastly, we examine, by means of pseudo panel data models, the possible influence of various kinds of unobserved heterogeneity on estimated price and income responses. In many of the models, we obtain negative and significant price elasticities and positive and significant income elasticities, although the size of the estimates vary, depending on the model applied, on the main drug for injecting, and on whether the consumer also is a dealer.

Biørn, Erik; Hagen, Terje P.; Iversen, Tor & Magnussen, Jon (2002). The Effect of ActivityBased Financing on Hospital Efficiency: A Panel Data Analysis of DEA Efficiency Scores 19922000. HERO skriftserie / Working paper. 8.

Biørn, Erik & Skjerpen, Terje (2002). Aggregation and Aggregation Biases in Production Functions: A Panel Data Analysis of Translog Models.
Vis sammendrag
An applied econometric study of aggregation, based on an unbalanced panel data set for manufacturing plants is presented. Panel data are informative in examining aggregation of variables, parameters, and relationships empirically since they (i) allow estimation at both the micro and the macro level, and (ii) enable comparison of the time series properties of the exactly aggregated micro relationships with those obtained by performing aggregation by analogy. Numerical aggregation of Translog production functions for three manufacturing industries is considered. We show, under linear aggregation of inputs and output, that departures between geometric and arithmetic means of the inputs and correlation between the loginputs, both their levels and time paths, contribute substantially to aggregation biases in the output volume and instability of the derived input and scale elasticities. Hence, the existence and stability of an approximate 'macro Translog production function' over time can be questioned.

Biørn, Erik & Skjerpen, Terje (2001). Aggregering og aggregeringsskjevhet i produktfunksjoner: En paneldataanalyse av en translogmodell.

BrettevilleJensen, Anne Line & Biørn, Erik (2001). Estimating Addicts' Price Response of Heroin: A Panel Data Approach Based on a Reinterviewed Sample. Memorandum fra Sosialøkonomisk institutt. 8.
Vis sammendrag
Drug abuse inflicts considerable harm on users, nonusing persons and on society, and a variety of means to curtail consumption of illegal drugs have been adopted. The consumption of drugs differ from consumption of most other goods in that it involves addiction. Intertemporal models are needed to encompass this aspect. The data for this study have been collected through interviews with heroin injectors attending a needle exchange service in Oslo, and the respondents have undergone a second interview about one year after the first. Four regression models will be considered: two are static panel data models and two are crosssection models with lagged or leaded drug consumption as additional regressors. Each model comes in two versions, one for nondealers and one for dealers of heroin. Despite our relatively small sample, we obtain negative and statistically significant price responses and positive and significant income responses for nearly all the models and specifications applied. The results from the two classes of models reflect the same picture although the absolute values of the elasticities vary. For the price elasticity, dealers obtain values in the range of [0.25,1.55] and nondealers in the range of [0.72,1.83]. Somewhat surprisingly, we obtain low estimates for the habit component in the panel data model, but higher for nondealers than for dealers.

Biørn, Erik (2001). How is Generalized Least Squares Related to Within and Between Estimators in Unbalanced Panel Data?.
Vis sammendrag
For a random effects regression model with unbalanced panel data, we demonstrate that the Generalized Least Squares (GLS) estimator can be expressed as a (matrix) weighted average of estimators which utilize the within individual and the between individual variation in the data set. We thus generalize a relationship familiar for balanced panel data. Specific attention must be given to the intercept of the regression. We also define an estimator containing the GLS, the within individual, and the between individual estimators for balanced and unbalanced data as special cases.

Biørn, Erik (2001). Paneldataøkonometri: Status og nyere utviklingslinjer.

Biørn, Erik (2001). The Efficiency of Panel Data Estimators: GLS Versus Estimators Which Do Not Depend on Variance Components.
Vis sammendrag
For a balanced panel data regression model with random effects, we discuss the efficiency of the GLS estimator relative to the OLS, the between, and the within estimators. Focus is on how the efficiency responds to changes in (a) the relative variance components and (b) the composition of the regressor covariance matrix which into between and within variation. Both oneway and twoway models are considered. For the oneway, one regressor model, we show that (i) OLS has maximal inefficiency relative to GLS when the within and between individual variation in the regressor account for the same part of the total variation, (ii) the between estimator is always less efficient than the OLS estimator. For the twoway, one regressor model, the between individual (between period) estimator is more efficient than OLS if the between period (between individual) share of the total variation in the regressor and/or the time specific (individual specific) disturbance variance component are sufficiently large. Illustrations relating to marginal budget shares in household consumption are given.

Wangen, Knut Reidar & Biørn, Erik (2001). Individual Heterogeneity and Price Responses in Tobacco Consumption: A TwoCommodity Analysis of Unbalanced Panel Data.
Vis sammendrag
The paper presents a panel data analysis of tobacco demand. The purpose is threefold: (i) to measure income, ownprice, and crossprice responses for two tobacco commodities: cigarettes and handrolling tobacco, (ii) to investigate sociodemographic effects, and (iii) to utilize the potential offered by panel data to investigate unobserved heterogeneity. The latter is crucial for commodities where consumers have different tastes and where users tend to become addicted. Several linear and nonlinear specifications of a twoequation system are estimated, using an unbalanced panel data set of Norwegian households over the period 1975  1994 and a modified Maximum Likelihood procedure. Differences between the results based on the subsample of smokers and on the pooled sample of smokers and nonsmokers are interpreted. For both commodities we find a high degree of unobserved heterogeneity and several robust and `theory consistent' patterns with respect to price responses and demographic effects.

Wangen, Knut Reidar & Biørn, Erik (2001). Prevalence and Substitution Effects in Tobacco Consumption: A Discrete Choice Analysis of Panel Data.
Vis sammendrag
This paper analyzes tobacco demand within a discrete choice framework. Using binomial and multinomial logit models with random effects, and an unbalanced panel data set of Norwegian households over a twenty year period, we first consider the decisions a) whether to smoke or not, and b) given the choice is to smoke, whether to smoke hand rolled or manufactured cigarettes. Next, we consider a multinomial logit framework, in which the households choose between no tobacco, only manufactured cigarettes, only hand rolled cigarettes, and a combination of manufactured and hand rolled cigarettes. In this process, we utilize the potential offered by panel data to investigate unobserved heterogeneity, which is crucial for commodities where consumers have different tastes and where users tend to become addicted. Using Maximum Likelihood in combination with bootstrap estimation of standard errors, we find that income and prices influence the `type of tobacco choice probabilities' at least as strongly as the `smoking/nonsmoking probabilities'. Cet.par., an increase in the price of manufactured cigarettes could lead consumers to switch to hand rolled cigarettes, rather than quit smoking. Sociodemographic variables seem to be at least as important in explaining the discrete aspects of tobacco consumption as income and prices. Finally, we find significant unobserved household specific effects in the smoking pattern.

Biørn, Erik; Lindquist, KjerstiGro & Skjerpen, Terje (2000). Micro Data on Capital Inputs: Attempts to Reconcile Stock and Flow Information.

Biørn, Erik & Skjerpen, Terje (2000). Heterogenitet i skalaegenskaper: En analyse med stokastiske koeffisienter og ubalanserte paneldata.

Biørn, Erik (2000). The Rate of Capital Retirement: How is it Related to the Form of the Survival Function and the Investment Growth Path?.
Vis sammendrag
We discuss the relationship between the retirement process of the capital, as formalized by its survival function, and the average retirement rate, and how this relationship is affected by changes in the investment path. The effect of the survival function on the age distribution of the capital goods, both those existing and those retired in each period, is also considered. These issues are illustrated by means of parametric (convex and concave) functions and numerical examples. We find that the retirement rate is a declining function of the growth rate of investment (except in the exponential decay case) and quite sensitive to the value of this parameter over a reasonable interval. Approximating the retirement rate by the inverse of the capital's maximal lifetime or twice this value (`double declining balance') will in many cases produce very inaccurate results. The response of the capital/investment ratio and the retirement/investment ratio to changes in the investment growth rate and in the curvature of the survival function is also investigated

Biørn, Erik; Lindquist, KjerstiGro & Skjerpen, Terje (2000). Heterogeneity in Returns to Scale: A Random Coefficient Analysis with Unbalanced Panel Data.
Vis sammendrag
This paper analyses the importance of scale economies by means of unbalanced plantlevel panel data from three Norwegian manufacturing industries. Focus is on heterogeneous technologies, and unlike most previous work on micro data, the model description includes heterogeneity in both the scale properties (the slope coefficients) and the intercept term, represented by random coefficients in the production function. Three (nested) functional forms are investigated: the Translog, an extended CobbDouglas, and the strict CobbDouglas. Although constant or weakly increasing returns to scale is found for the average plant, the results reveal considerable variation across plants. Variations in both input and scale elasticities are to a larger extent due to randomness of the production function parameters than to systematic differences in the input mix.

Biørn, Erik; Lindquist, KjerstiGro & Skjerpen, Terje (2000). Micro Data on Capital Inputs: Attempts to Reconcile Stock and Flow Information.
Vis sammendrag
We evaluate consequences of some important assumptions of the perpetual inventory method of capital stock calculation under geometric depreciation. The data are plantlevel panel data from the Norwegian manufacturing statistics, containing independent measures of capital stocks and gross investment flows for two capital types and three industries. First, we look at consequences of choosing different depreciation rates a priori, when we use as benchmark for the level of the capital stocks deflated fire insurance values in a specific year. The choice of depreciation rate is of substantial importance, some values resulting in decreasing, other in increasing capital stocks over time. Second, we attempt to estimate depreciation rates by combining time series on gross investment and fire insurance values for the same period. In our regression models, both systematic and random measurement errors in the fire insurance values and various forms of heterogeneity in the coefficient structure are represented. We conclude that the estimated depreciation rates vary significantly with the specification of the measurement error process and that heterogeneity in this process across plants is important.

Biørn, Erik (1999). Trygve Haavelmo, 1911  1999. Tilfeldig gang.
ISSN 08038953.
16(2), s 32 33

Biørn, Erik & Skjerpen, Terje (1999). Kapitalberegninger på mikrodata.

Biørn, Erik (1999). Estimating Regression Systems from Unbalanced Panel Data: A Stepwise Maximum Likelihood Procedure.
Vis sammendrag
In this paper, we consider the formulation and estimation of systems of regression equations with random individual effects in the intercept terms from unbalanced panel data, i.e., panel data where the individual time series have unequal length. Generalized Least Squares (GLS) estimation and Maximum Likelihood (ML) estimation are discussed. A stepwise algorithm for solving the ML problem is developed.

Biørn, Erik (1999). Random Coefficients in Regression Equation Systems: The Case with Unbalanced Panel Data.
Vis sammendrag
We consider a framework for analyzing panel data characterized by: (i) a system of regression equations, (ii) random individual heterogeneity in both intercepts and slope coefficients, and (iii) unbalanced panel data, i.e., panel data where the individual time series have unequal length. A Maximum Likelihood (ML) procedure for joint estimation of all parameters is described. Since it is complicated to implement in numerical calculations, we consider simplified procedures, in particular for estimating the covariance matrices of the random coefficients. An algorithm for modified ML estimation of all parameters is presented.

Biørn, Erik (1998). Panel Data with Measurement Errors: Instrumental Variables and GMM Procedures Combining Levels and Differences.

Biørn, Erik (1998). Panel Data with Measurement Errors: Instrumental Variables and GMM Procedures Combining Levels and Differences.
Vis sammendrag
The estimation of linear, static regression equations from panel data with measurement errors in the regressors is considered. If the latent regressor is autocorrelated or nonstationary, several consistent instrumental variables (IV) and generalized method of moments (GMM) estimators usually exist, provided some structure is imposed on the disturbances and measurement errors. Applications of GMM procedures (i) on equations in differences with IV's in levels and (ii) on equations in levels with IV's in differences  the difference transformations eliminating unobserved individual heterogeneity  are considered. The IV's may be constructed from values of the regressors or the regressand. Some of the orthogonality conditions delimiting the valid IV's are redundant. Illustrations based on data on inputs and outputs from an eight year panel of manufacturing firms are given.

Biørn, Erik; Lindquist, KjerstiGro & Skjerpen, Terje (1998). Random Coefficients and Unbalanced Panels: An Application on Data from Norwegian Chemical Plants.
Vis sammendrag
A framework for analyzing substitution and scale properties, and technical change from plantlevel panel data is presented. Focus is on comparing the constant and random coefficient specification of the substitution and scale parameters and investigating the potential variation of the parameters across firms. Characteristics of the model framework are (i) an equation system consisting of a threefactor translog cost function and the corresponding costshare equations, (ii) random firm specific heterogeneity in coefficients, and (iii) a Maximum Likelihood procedure allowing for unbalanced panel data. The empirical results, based on data from Norwegian chemical plants, indicate substantial firm specific heterogeneity in substitution and scale properties.

Biørn, Erik (1997). Analyse av paneldata med målefeil.

Biørn, Erik & Klette, Tor Jakob (1997). Panel Data with ErrorsinVariables: A Note on Essential and Redundant Orthogonality Conditions in GMMEstimation. Discussion Papers. 190.
Vis sammendrag
General Method of Moments (GMM) estimation of a linear oneequation model using panel data with errorsinvariables is considered. To eliminate fixed individual heterogeneity, the equation is differenced across one or more than one periods and estimated by means of instrumental variables. With nonautocorrelated measurement error, we show that only the oneperiod and a few twoperiod differences are essential, i.e. relevant for GMMestimation. GMM estimation based on all orthogonality conditions on the basis of a generalized inverse formulation is shown to be equivalent to estimation using only the essential orthogonality conditions.

Biørn, Erik (1997). Panel Data, Heterogeneity, and Aggregation: A General Moment Estimator with Applications.
Vis sammendrag
A linear equation for panel data with twoway random or fixed effects and a set of individual specific and period specific `within individual' and `within period' estimators of its coefficient vector are considered. Each estimator can be given an Ordinary Least Squares (OLS) or an Instrumental Variables (IV) interpretation. A general moment estimator, obtained by an arbitrary weighting of these `disaggregate' OLS and IV estimators is introduced. Nine wellknown estimators utilizing the entire data set, including `within', `between', OLS, and GLS estimators, emerge as special cases. Issues of robustness to simultaneity and measurement errors are discussed. An empirical illustration is given.

Biørn, Erik & Klette, Tor Jakob (1997). Variable Differencing and GMM Estimation with Panel Data with ErrorsinVariables.
Vis sammendrag
Procedures for estimating a linear singleequation model by means of panel data with errorsinvariables are considered. To eliminate fixed individual heterogeneity, the equation is differenced across one or more than one periods. The differenced equations can be estimated by using as instruments for the differenced errorridden regressor, level values of this regressor (both leads and lags). General Method of Moments (GMM) procedures for the complete system of differenced equations are considered. The distinction between essential and redundant orthogonality conditions is important, and we consider ways of treating the redundant conditions. Empirical illustrations based on Norwegian establishment panel data on labor input and output are given.

Biørn, Erik (1996). Anvendt økonometri  utvalgte emner, annen utgave: Del I (kapittel 1  9), del II (kapittel 10  13).

Biørn, Erik (1996). Prediksjon av økonomiske variable ved hjelp av regresjonsmodeller.

Biørn, Erik (1996). The Labour Demand Response to Permanent Changes in Output: Errors in Variables Econometrics Based on Panel Data.

Biørn, Erik (1996). The Labour Demand Response to Permanent Changes in Output: Errors in Variables Econometrics Based on Panel Data.

Biørn, Erik & Klette, Tor Jakob (1996). The Labour Input Response to Permanent Changes in Output: Errors in Variables Econometrics Based on Panel Data.
Vis sammendrag
Using panel data for Norwegian manufacturing, we revisit `the increasing returns to scale puzzle' for labour inputs. We consider the response of the input of white collar workers, blue collar workers, and blue collar worker hours to permanent changes in output. Permanent and temporary changes in output are treated as latent variables within a GMM estimation procedure. We compare OLS, IV, and GMM estimates of the response elasticities and conclude that the distinction between permanent and temporary changes is essential. Our final GMM estimates suggest that the `increasing returns to scale puzzle' remains for all labour inputs also when we consider the response to permanent changes in output. For materials, the output response indicates approximately constant returns to scale. This suggests nonhomotheticity of the production technology.

Biørn, Erik (1989). Om Trygve Haavelmos bidrag til økonometri. Sosialøkonomen.
ISSN 00381624.
43(11), s 6 11
Se alle arbeider i Cristin
Publisert 30. sep. 2010 10:45
 Sist endret 20. des. 2017 15:30