Potential prediction bias in regression and discriminant analysis

Abstract
Prediction bias is the difference between a model's apparent and actual prediction errors. Prediction bias is likely to occur when a model contains many independent variables relative to sample size or when many different sets of independent variables are tested by a stepwise procedure. Examples of potential prediction bias are illustrated by comparing published models with models developed using random numbers. Model prediction bias can be estimated by using a resampling procedure called the bootstrap. The bootstrap procedure is illustrated with a simple example.

This publication has 2 references indexed in Scilit: