Abstract
This paper presents a critique of the standard two-stage approach in which a well-fitting model is identified first, and then applied in one or several subsequent inferences. Although deeply ingrained in practice, this approach is defi- cient because the possibility of an erroneous decision in the model selection (model uncertainty) is discounted. The criticism applies to all model selection procedures, equally in the frequentist and Bayesian perspectives. We describe an approach based on synthetic estimation, in which the estimators based on the candidate models are linearly combined. Its properties are explored in the setting of an experiment from information technology.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Draper, D.N.: Assessment and propagation of model uncertainty. J. Royal Stat. Soc. B, 57, 45–98 (1995)
Fay, R.E., Herriot, R.A.: Estimation of income for small places: an application of James-Stein procedures to census data. J. Amer. Stat. Assoc., 74, 269–277 (1979)
Hoerl, A.E., and Kennard, R.W.: Ridge regression: biased estimation for non-orthogonal problems. Technom., 12, 55–67 (1970)
Hoeting, J., Madigan, D., Raftery, A. E., Volinsky, C. T.: Bayesian model averaging: A tutorial. Stat. Sci., 14, 381–417 (1999)
Kass, R.E., Raftery, A.E.: Bayes factors. J. Amer. Stat. Assoc., 90, 773–795 (1995)
Lindley, D.V.: The philosophy of statistics (with comments). J. Royal Stat. Soc. D, 49, 293–337 (2000)
Longford, N.T.: Multivariate shrinkage estimation of small area means and proportions. J. Royal Stat. Soc. A, 162, 227–245 (1999)
Longford, N.T.: An alternative to model selection in ordinary regression. Stat. Comput., 13, 67–80 (2003)
Longford, N.T.: Missing Data and Small-Area Estimation. Modern Analytical Equipment for the Survey Statistician. Springer-Verlag, New York (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Physica-Verlag Heidelberg
About this paper
Cite this paper
Longford, N.T. (2006). Is ‘Which model . . .?’ the right question?. In: Rizzi, A., Vichi, M. (eds) Compstat 2006 - Proceedings in Computational Statistics. Physica-Verlag HD. https://doi.org/10.1007/978-3-7908-1709-6_26
Download citation
DOI: https://doi.org/10.1007/978-3-7908-1709-6_26
Publisher Name: Physica-Verlag HD
Print ISBN: 978-3-7908-1708-9
Online ISBN: 978-3-7908-1709-6
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)