Construct validity and other issues pertaining to 'The impact of research designs on R2 in linear regression models: An exploratory meta-analysis.

Raymond Hubbard (1997)

INTRODUCTION

I initially commented on Heribert Reisinger's (1997) paper, "The impact of research designs on R2 in linear regression models: An exploratory meta-analysis," in a double-blind review context. Some of my comments are incorporated in his present paper, while others are not. Unfortunately, my major original criticism of Reisinger's work, namely, that it suffers from serious construct validity problems, has not been addressed in the revised version of the manuscript. This is because it is all but impossible to do so. Nevertheless, the construct validity problems in Reisinger's paper impede any meaningful interpretation of his meta-analytic results. This issue is discussed below.

 

download the complete article in PDF