-
Schweder, Tore
(2015).
Confidence is epistemic probability.
-
Schweder, Tore & Hjort, Nils Lid
(2014).
Optimal and approximate likelihood.
-
Schweder, Tore
(2013).
Integrating confidence intervals, likelihoods and condence distrubutions.
-
Henderiks, Jorijntje; Gerecht, Andrea; Hannisdal, Bjarte; Liow, Lee Hsiang; Reitan, Tore & Schweder, Tore
[Vis alle 7 forfattere av denne artikkelen]
(2013).
PhytoSCALE project: calibrating phytoplankton cell size as a proxy for climatic adaptation.
-
Schweder, Tore & Hjort, Nils Lid
(2013).
Confidence Distribution, the Frequentist Distribution Estimator of a Parameter: A Review Discussions.
International Statistical Review.
ISSN 0306-7734.
81(1),
s. 56–68.
doi:
10.1111/insr.12004.
-
Schweder, Tore
(2012).
Confidence distributions and confidence likelihood: distributional inference without priors.
-
Hjort, Nils Lid & Schweder, Tore
(2012).
Structure and Uncertainty: Confidence and Likelihood.
-
Schweder, Tore
(2012).
Causal sufficiency and Markov Completeness.
-
Schweder, Tore
(2012).
Confidence distributions and confidence likelihood: distributional inference without priors.
-
-
Henderiks, Jorijntje; Hannisdal, Bjarte; Rickaby, Rosalind E. M.; Liow, Lee Hsiang; Reitan, Trond & Schweder, Tore
(2010).
Phytoplankton size: climatic adaptation and long-term evolution.
-
Schweder, Tore & Sadykova, Dinara
(2007).
Event history models for capture-recapture surveys with passively marked individuals.
-
Schweder, Tore & Sadykova, Dinara
(2007).
Event history models for capture-recapture surveys with passively marked individuals.
-
Schweder, Tore & Sadykova, Dinara
(2007).
Rough Modeling of complex photo-ID data for BCB bowhead whales.
-
Schweder, Tore; Sadykova, Dinara; Rugh, D.J. & Koski, W.R
(2007).
Modeling of complex photo-ID data for BCB bowhead whales.
-
Jorde, Per Erik; Schweder, Tore & Stenseth, Nils Christian
(2004).
The Bering-Chukchi-Beaufort stock of bowhead whales: one homogenous population?
-
-
Schweder, Tore
(2003).
Sjangerbrudd eller vitenskapelig uredelighet i Lomborgsaken?
Økonomisk forum.
ISSN 1502-6108.
8(3),
s. 1–4.
-
-
Schweder, Tore
(2002).
Forkludring av vitenskapelig usikkerhet - erfaringer fra Hvalfangstkommisjonen.
Cicerone.
ISSN 0804-0508.
s. 13–15.
Vis sammendrag
Forskere kan fuske på flere måter. En av dem er å forkludre den vitenskapelige usikkerheten ved å konstruere opp eller provosere fram unødige uenigheter og kontroverser. Dette har skjedd ved flere anledninger i Den internasjonale hvalfangskomisjonen.
-
Schweder, Tore
(2002).
The history of statistics in Norway - told by historians.
Vis sammendrag
Lie, E. and Roll-Hansen, H. 2001. Faktisk talt - statistikkens historie i Norge (Factually speaking - The history of statistics in Norway), Universitetsforlaget, is written by two historians. I will comment on this book of 481 pages by asking two questions: (i) What is statistics to the historians, and what do they see as the place of statistics in in the shaping of the Norwegian society? And (ii) what have they found that is of particular interest to the general historian of statistics? Among other things, the authors have brought to the light a debate between Anders Kiær who used his representative method (survey sampling) to investigate the costs of introducing a public and universal pension scheme for old and disabled (proposed in 1894), and Jens Hjorth who used actuarial and statistical methods to argue that Kiær's survey gave biased results. Hjorth won the debate, and Kiær became silent about his representative method - while survey sampling was gaining growing attention internationally.
-
Schweder, Tore
(2002).
Frequentist versions of posteriors and priors.
Vis sammendrag
Confidence distributions are Neyman's interpretation of Fisher's fiducial distributions. They are the frequentist's analogues of Bayesian priors and posteriors. The quantiles of a confidence distribution are end points of confidence intervals for the parameter in question. To combine a prior confidence distribution with the likelihood of new data, it must be converted to a likelihood summarizing the past data. The two likelihood components are then multiplied together, and posterior confidence distributions are obtained for the parameters of interest, often through a parametric bootstrap experiment. The likelihood related to a confidence distribution is in general different from the confidence density. A version of the Neyman-Pearson theorem is proved for confidence distributions. The frequentist approach is illustrated on capture-recapture data for bowhead whales, and is compared to the Bayesian approach with respect to bias and other issues
-
Schweder, Tore
(2001).
Statistical Methods, History of: Post-1900.
I Smelser, Neil J. & Baltes, Paul B (Red.),
International Encyclopedia of the Social & Behavioral Sciences.
Elsevier.
ISSN 0-08-043076-7.
s. 15031–15037.
-
Schweder, Tore
(2001).
Skepsisens plass i biologien - om falske funn og fordreid usikkerhet.
Biolog.
ISSN 0801-0722.
19(3/4),
s. 6–12.
Vis sammendrag
På bakgrunn av diskusjon om parapsykologi og om hval og hvalfangst innen IWC, settes sunn skepsis opp mot notorisk skepsis av kverulantisk art. Usunn og vedvarende skepsis kan undergrave forskningsprosessens integritet, og kan i ekstreme tilfeller regenes som uskikk i forskningen, på linje med fabrikasjon og falsifikasjon.
-
Schweder, Tore
(2001).
The Neyman-Pearson lemma for confidence distributions.
-
Schweder, Tore
(2001).
Discrete distance sampling with difficulties.
-
Schweder, Tore
(2001).
Fishers paradigmerevolusjon, et 79-års jubileum.
-
Schweder, Tore
(2001).
Olav Reiersøl - statistiker, økonometriker og esperantist.
Vis sammendrag
Reiersøl var professor i matematisk statistikk fra 1961. Før det var han dosent og professor i matematikk, men hele tiden matematisk statistiker. Han døde i februar, nesten 93 år gammel. Reiersøls hovedfunn var at den enkleste konfluensanalysesmodellen til Frisch bare var uidentifiserbar når de latente variablene var normalfordelte. Hva betyr dette, hvorfor er det et viktig funn og hvordan kom Reiersøl til å interessere seg for dette spørsmålet? Hva ellers fant Reiersøl i sin forskning? Var han like en like original forsker som person, veileder og lærer?
-
Schweder, Tore
(2001).
Minnetale over Olav Reiersøl.
-
Schweder, Tore
(2001).
Abundance estimation from photo-identification data: confidence distributions and reduced likelihood for bowhead whales off Alaska.
-
Schweder, Tore
(2001).
Revolusjoner og kontrarevolusjoner i teoretisk statistikk - kan frekventistisk Bayesianisme bringe varig fred?
-
Schweder, Tore
(2000).
Frequentist versions of posteriors and priors.
Vis sammendrag
Confidence distributions (Fisher's fiducial distributions) are the frequentist's analogues of Bayesian priors and posteriors. The quantiles of a confidence distribution are end points of confidence intervals for the parameter in question. To combine a prior confidence distribution with the likelihood of new data, it must be converted to a likelihood summarizing the past data. The two likelihood components are then multiplied together, and posterior confidence distributions are obtained for the parameters of interest. This frequentist approach is compared to the Bayesian approach with respect to bias and other issues.
-
Schweder, Tore
(2000).
Confidence distributions and likelihood.
Vis sammendrag
Confidence distributions are the frequentist's analogues of Bayesian priors and posteriors. Being a frequentist concept, the possible bias in a confidence distribution is well defined. Approximately unbiased posterior confidence distributions are obtained by bootstrapping of the likelihood based on the data and on possible prior confidence distributions based on previous data. As distinct from Bayesian analysis, information on the probability basis of a prior distribution is necessary to combine it with the data likelihood. Being a likelihood analysis, no problem arise if there are more or fewer prior distributions (with corresponding likelihood components) than there are free parameters in the model.
-
Schweder, Tore
(2000).
Integrative fish stock assessment by frequentist methods: confidence distributions and likelihoods for bowhead whales.
Vis sammendrag
Frequentism in theoretical statistics evolved from R.A. Fisher's paradigmatic revolution in 1922, which partly was against the then prevailing Bayesianism. We now see a counter-revolution in fisheries and also elsewhere: back to Bayes. Is it necessary to depart from Fisher's methodology to use distributions as inputs and outputs of statistical analysis, and to integrate diverse data? Or can Fisher deliver the main attractions of Bayes, without some of the disturbing shortcomings? The frequentist methodology to be sketched is illustrated on data concerning bowhead whales. It involves the integration of diverse data, via the likelihood; the use of confidence distributions for inference about interest parameters; and obtaining confidence distributions and their accompanying reduced likelihoods through simulation experiments. A reduced likelihood summarizes the information in the data regarding a specific parameter, and might be used in later meta analyses. The approach might be attractive in the scientific context, where subjectivity should be kept to a minimum, where results should be unbiased and where the statistical uncertainty needs to be presented in the format of a distribution.
-
Schweder, Tore
(2000).
Confidence distributions and reduced likelihood.
-
Schweder, Tore
(2000).
Bør høye kvoter kappes ned? Bioøkonomisk modellering og simulering av torskefisket.
-
Schweder, Tore
(2000).
Bør høye kvoter kappes ned? Bioøkonomisk modellering og simulering av torskefisket.
Vis sammendrag
Fisket reguleres nå stort sett på biologisk grunnlag. Kvotene varierer
kraftig. Systemet i Barentshavet er modellert og simulering viser at
lønnsomheten i fisket og samfunnets ressursrente bedres ved å kappe
kvotene ned til et velvalgt øvre tak når de er høye. Overraskende nok
blir ikke fangstene redusert i det lange løp ved fornuftig
kvotekapping. En geometrisk versjon av den stokastiske
Ornstein-Uhlenbeck prosessen blir også diskutert i dette perspektivet.
-
Diekert, Florian Klaus; Schweder, Tore & Lund, Kristen
(2014).
From Open-Access to Individual Quotas: Disentangling the Effects of Policy Reform and Environmental Changes in the Norwegian Coastal Cod Fishery.
Økonomisk Institutt, UiO.
ISSN 0809-8786.
-
Witting, Lars & Schweder, Tore
(2008).
Lower confidence bound on population status from catch sex ratio: applied to minke whales off West Greenland.
International Whaling Commission.
Vis sammendrag
Lower confidence bounds on carrying capacity is estimated by parametric bootstrapping in the case of infinte maximum likelihood estimate.
-
-
-
-
-
-
Aldrin, Magne & Schweder, Tore
(2005).
Revision of RMP – Status of ongoing work at the Norwegian Computing Center. IWC/SC/57/RMP3.
International Whaling Commission.
-
Schweder, Tore; Jorde, Per Erik & Stenseth, Nils Christian
(2005).
Temporal genetic pattern in BCB bowhead whales in the fall migration at Barrow: a reflection of a structured population? IWC/SC/57/BRG10.
International Whaling Commission.
-
-
Hagen, Gro Synøve; Høst, Gudmund & Schweder, Tore
(2003).
Harp Seal in the Scenario-C Model.
Norsk Regnesentral.
-
-
Fleischer, Luis A. & Schweder, Tore
(2002).
Gray whales on their winter grounds in Baja California Sur, México (1980-1998).
International Whaling Commission.
54(BRG11).
Vis sammendrag
Temporal and seasonal patterns of abundance of adults and calves were estimated by generalized linear models from weakly counts obtained from shipborn and aerial surveys.
-
Berg, Erlend; Schweder, Tore & Tvete, Ingunn Fride
(2001).
Statistisk modellering av kommersielle fangstdata; en illustrasjon basert på trålfangster av torsk i 1999.
Norsk Regnesentral.
-
-
Schweder, Tore & Hjort, Nils Lid
(2001).
Confidence and Likelihood.
Økonomisk institutt.
ISSN 0801-1117.
-
Hirst, David; Høst, Gudmund; Schweder, Tore; Fotland, Åge; Jakobsen, Tore & Skaug, Hans Julius
[Vis alle 8 forfattere av denne artikkelen]
(2000).
Towards a statistical model for the uncertainty in fisheries data for stock asssessment in the Barents Sea.
Norsk Regnesentral.
-
Schweder, Tore & Hjort, Nils Lid
(1999).
Frequentist analogues of priors and posteriors.
Department of Mathematics, University of Oslo.
ISSN 82-553-1174-2.