Measuring overfitting and mispecification in nonlinear models
AbstractWe start by proposing a new measure of overfitting expressed on the untransformed scale of the dependent variable, which is generally the scale of interest to the analyst.We then show that with nonlinear models shrinkage due to overfitting gets confounded by shrinkage—or expansion— arising from model misspecification. Out-of-sample predictive calibration can in fact be expressed as in-sample calibration times 1 minus this new measure of overfitting. We finally argue that re-calibration should be performed on the scale of interest and provide both a simulation study and a real-data illustration based on health care expenditure data.
Download InfoIf you experience problems downloading a file, check if you have the proper application to view it first. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.
Bibliographic InfoPaper provided by HEDG, c/o Department of Economics, University of York in its series Health, Econometrics and Data Group (HEDG) Working Papers with number 11/25.
Date of creation: Aug 2011
Date of revision:
Contact details of provider:
Postal: HEDG/HERC, Department of Economics and Related Studies, University of York, York, YO10 5DD, United Kingdom
Phone: (0)1904 323776
Fax: (0)1904 323759
Web page: http://www.york.ac.uk/economics/postgrad/herc/hedg/
More information through EDIRC
overfitting; shrinkage; misspecification; forecasting; health care expenditure;
This paper has been announced in the following NEP Reports:
- NEP-ALL-2011-08-15 (All new papers)
- NEP-ECM-2011-08-15 (Econometrics)
- NEP-FOR-2011-08-15 (Forecasting)
- NEP-HEA-2011-08-15 (Health Economics)
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- Blough, David K. & Madden, Carolyn W. & Hornbrook, Mark C., 1999. "Modeling risk using generalized linear models," Journal of Health Economics, Elsevier, vol. 18(2), pages 153-171, April.
- Willard G. Manning & Anirban Basu & John Mullahy, 2003.
"Generalized Modeling Approaches to Risk Adjustment of Skewed Outcomes Data,"
0313, Harris School of Public Policy Studies, University of Chicago.
- Manning, Willard G. & Basu, Anirban & Mullahy, John, 2005. "Generalized modeling approaches to risk adjustment of skewed outcomes data," Journal of Health Economics, Elsevier, vol. 24(3), pages 465-488, May.
- Willard G. Manning & Anirban Basu & John Mullahy, 2003. "Generalized Modeling Approaches to Risk Adjustment of Skewed Outcomes Data," NBER Technical Working Papers 0293, National Bureau of Economic Research, Inc.
- Manning, Willard G. & Mullahy, John, 2001.
"Estimating log models: to transform or not to transform?,"
Journal of Health Economics,
Elsevier, vol. 20(4), pages 461-494, July.
- Willard G. Manning & John Mullahy, 1999. "Estimating Log Models: To Transform or Not to Transform?," NBER Technical Working Papers 0246, National Bureau of Economic Research, Inc.
- Anirban Basu & Bhakti V. Arondekar & Paul J. Rathouz, 2006. "Scale of interest versus scale of estimation: comparing alternative estimators for the incremental costs of a comorbidity," Health Economics, John Wiley & Sons, Ltd., vol. 15(10), pages 1091-1107.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Jane Rawlings).
If references are entirely missing, you can add them using this form.