Published
Decision Theory for the Variance Ratio in One-Way ANOVA with Random Effects
Teoría de la decisión para la relación de las varianzas en el análisis de la varianza de un factor con efectos aleatorios
DOI:
https://doi.org/10.15446/rce.v38n1.48810Keywords:
Analysis of Variance with Random Effects, Decision, Equilibrium, Expected Loss, Variance Ratio (en)Análisis de varianza con efectos aleatorios, Decisión, Equilibrio, Pérdida esperada, Tazón de la varianza. (es)
Estimating a variance component in the model of analysis of variance with random effects and testing the hypothesis that the variance vanishes are important issues in many applications. Such inferences are beyond the confines of the standard (asymptotic) theory because a zero variance is on the boundary of the parameter space and the maximum likelihood or another reasonable estimator of variance has a non-trivial probability of zero in many settings. We derive decision rules regarding the variance ratio in balanced one-way analysis of variance, in both the frequentist and Bayesian perspectives. We argue that this approach is superior to hypothesis testing because it incorporates the consequences of the two kinds of error (incorrect choice) that may be committed. An application to a track athlete’s training performance is presented.
La estimación de una de las varianzas en el modelo de análisis de la varianza con efectos aleatorios y la prueba de hipótesis de que la varianza se anula, son temas importantes en muchas aplicaciones. Tales inferencias están fuera de los confines de la teoría asintótica estándar porque una varianza cero está en la frontera del espacio paramétrico y la máxima verosimilitud u otro estimador razonable de una varianza tiene una probabilidad no trivial de cero en muchos contextos. Nosotros derivamos una regla de decisión sobre la razón de varianzas en un análisis de varianza de un factor balanceado tanto para la perspectiva frecuentista como la Bayesiana. Argumentamos que este enfoque es superior a la prueba de hipótesis porque incorpora las consecuencias de los dos tipos de error (elección incorrecta) que pueden cometerse. Se presenta una aplicación sobre los rendimientos de los entrenamientos de un atleta de pista.
References
Andrade, M., Longford, N. & Tovar, D. (2014), ‘Tests for spatial and temporal correlation in mixed models for climate data’, Revista Brasileira de Biometria 32, 229–255.
Berger, J. (1985), Statistical Decision Theory and Bayesian Analysis, 2 edn, Springer-Verlag, New York.
Crainiceanu, C. & Ruppert, D. (2004), ‘Likelihood ratio tests in linear mixed models with one variance component’, Journal of the Royal Statistical Society. Series B 66, 165–185.
DeGroot, M. (1970), Optimal Statistical Decisions, McGraw-Hill, New York.
Dempster, A., Laird, N. & Rubin, D. (1977), ‘Maximum likelihood from incomplete data via the EM algorithm’, Journal of the Royal Statistical Society. Series B 39, 1–38.
Fisher, R. (1935), ‘The fiducial argument in statistical inference’, Annals of Eugenics 6, 391–398.
Fisher, R. (1956), Statistical Methods and Scientific Inference, Oliver and Boyd, Edinburgh.
Giampaoli, V. & Singer, J. (2009), ‘Likelihood ratio tests for variance components in linear mixed models’, Journal of Statistical Planning and Inference 139, 1435–1448.
Greven, S., Crainiceanu, C., Küchenhoff, H. & Peters, H. (2008), ‘Restricted likelihood ratio testing for zero variance components in linear mixed models’, Journal of Computational and Graphical Statistics 17, 870–891.
Hannig, J. (2009), ‘On generalized fiducial inference’, Statistica Sinica 19, 491–544.
Li, K., Meng, X.-L., Raghunathan, T. & Rubin, D. (1991), ‘Significance levels from repeated p values with multiply-imputed data’, Statistica Sinica 1, 65–92.
Lindley, D. (1985), Making Decisions, 2 edn, Wiley, Chichester, UK.
Little, R. & Rubin, D. (2002), Statistical Analysis with Missing Data, Wiley, New York.
Longford, N. (2000), ‘On estimating standard errors in multilevel analysis’, The Statistician 49, 389–398.
Longford, N. (2005), ‘Editorial: Model selection and efficiency. Is ‘Which model ...? the right question?’, Journal of the Royal Statistical Society. Series A 68, 469–472.
Longford, N. (2010), ‘Bayesian decision making about small binomial rates with uncertainty about the prior’, The American Statistician 64, 164–169.
Longford, N. (2012a), ‘Comparing normal random samples, with uncertainty about the priors and utilities’, Scandinavian Journal of Statistics 39, 729–742.
Longford, N. (2012b), ‘Which model? is the wrong question’, Statistica Neerlandica 66, 237–252.
Longford, N. (2013), Statistical Decision Theory, Springer-Verlag, Heidelberg, Germany.
Patterson, D. & Thompson, R. (1971), ‘Recovery of inter-block information when block sizes are unequal’, Biometrika 58, 545–554.
Potthoff, R., Woodbury, M. & Manton, K. (1992), ‘Equivalent sample size and equivalent degrees of freedom refinements for inference using survey weights under superpopulation models’, Journal of American Statistical Association 87, 383–396.
Robert, C. & Cassella, G. (2004), Monte Carlo Statistical Methods, 2 edn, Springer-
Verlag, New York.
Rubin, D. (2002), Multiple Imputation for Nonresponse in Surveys, Wiley, New York.
Searle, S., Casella, G. & McCulloch, C. (2006), Variance Components, 2 edn, Wiley, New York.
Seidenfeld, T. (1992), ‘R.A. Fisher’s fiducial argument and Bayes’ theorem’, Statistical Science 7, 358–368.
Dimensions
PlumX
Article abstract page views
Downloads
How to Cite
License
Copyright (c) 2015 Revista Colombiana de Estadística
This work is licensed under a Creative Commons Attribution 4.0 International License.
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
