MEASUREMENT ERROR IN THE ANALYSIS OF INTERACTION EFFECTS BETWEEN CONTINUOUS PREDICTORS USING MULTIPLE-REGRESSION - MULTIPLE INDICATOR AND STRUCTURAL EQUATION APPROACHES
J. Jaccard et Ck. Wan, MEASUREMENT ERROR IN THE ANALYSIS OF INTERACTION EFFECTS BETWEEN CONTINUOUS PREDICTORS USING MULTIPLE-REGRESSION - MULTIPLE INDICATOR AND STRUCTURAL EQUATION APPROACHES, Psychological bulletin, 117(2), 1995, pp. 348-357
Unreliability of measures produces bias in regression coefficients. Su
ch measurement error is particularly problematic with the use of produ
ct terms in multiple regression because the reliability of the product
terms is generally quite low relative to its component parts. The use
of confirmatory factor analysis as a means of dealing with the proble
m of unreliability was explored in a simulation study. The design comp
ared traditional regression analysis (which ignores measurement error)
with approaches based on latent variable structural equation models t
hat used maximum-likelihood and weighted least squares estimation crit
eria. The results showed that the latent variable approach coupled wit
h maximum-likelihood estimation methods did a satisfactory job of inte
raction analysis in the presence of measurement error in terms of Type
I and Type II errors.