create new tag
, view all tags, tagging instructions

Quadratic P-value

Lead Author(s): Peter Bacchetti, PhD

This is a P-value for the hypothesis that a numeric predictor has a linear effect. When P<0.05, this is usually interpreted as considerable evidence against this assumption, so you should consider alternatives, such as breaking the predictor into categories or modeling it more flexibly with polynomials or splines.

Topic revision: r5 - 25 Jun 2012 - 00:41:15 - PeterBacchetti

Copyright & by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding CTSPedia? Send feedback