Model Selection and Paradoxes of Prediction

10 Pages Posted: 7 Nov 2006

See all articles by Oleg Itskhoki

Oleg Itskhoki

Princeton University - Department of Economics

Multiple version iconThere are 2 versions of this paper

Date Written: January 18, 2005


In this essay we postulate a number of theoretical hypotheses allowing one to resolve in some degree the following two prediction paradoxes: (1) why simple linear models often have an advantage in predictive power over more complex nonlinear models that lead to a better in-sample fit; (2) why combinations of forecasts often increase the predictive power of individual forecasts. We also give a numerical example illustrating our theoretical statements.

Keywords: model selection, forecasting, linear and nonlinear models, combination of forecasts

JEL Classification: C10, C22, C53

Suggested Citation

Itskhoki, Oleg, Model Selection and Paradoxes of Prediction (January 18, 2005). Available at SSRN: or

Oleg Itskhoki (Contact Author)

Princeton University - Department of Economics ( email )

Fisher 306
Princeton, NJ 08544-1021
United States
+1 (609) 258-5493 (Phone)


Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
PlumX Metrics