Estimating prediction error: cross-validation vs. accumulated prediction error
2010 (English)In: Communications in statistics. Simulation and computation, ISSN 0361-0918, E-ISSN 1532-4141, Vol. 39, no 5, 880-898 p.Article in journal (Refereed) Published
We study the validation of prediction rules such as regression models and classification algorithms through two out-of-sample strategies, cross-validation and accumulated prediction error. We use the framework of Efron (1983) where measures of prediction errors are defined as sample averages of expected errors and show through exact finite sample calculations that cross-validation and accumulated prediction error yield different smoothing parameter choices in nonparametric regression. The difference in choice does not vanish as sample size increases.
Place, publisher, year, edition, pages
Informa plc. , 2010. Vol. 39, no 5, 880-898 p.
Local polynomial regression, Nonparametric regression, Out-of-sample validation, Smoothing parameter
Probability Theory and Statistics
Research subject Statistics
IdentifiersURN: urn:nbn:se:umu:diva-34149DOI: 10.1080/03610911003650409ISI: 000277568500002OAI: oai:DiVA.org:umu-34149DiVA: diva2:319164