INTERACTION, NONLINEARITY, AND MULTICOLLINEARITY - IMPLICATIONS FOR MULTIPLE-REGRESSION

被引:130
作者
CORTINA, JM
机构
关键词
D O I
10.1016/0149-2063(93)90035-L
中图分类号
F [经济];
学科分类号
02 ;
摘要
Moderated Hierarchical Multiple Regression (MHMR) is typically used to test for the presence of interactions. When an interaction term is composed of correlated variables, linearity and additivity become confounded. The result of this confounding is that an interaction term in MHMR may be statistically significant only because of its overlap with unmeasured nonlinear terms. I recommend that squared terms be used as covariates in such situations and show that the resulting loss of power with respect to the test of significance for the interaction term is limited to that associated with the loss of degrees of freedom and is therefore negligible if it exists at all.
引用
收藏
页码:915 / 922
页数:8
相关论文
共 20 条
[1]  
Althauser RP, 1971, CAUSAL MODELS SOCIAL
[2]  
[Anonymous], 1971, STAT PRINCIPLES EXPT
[3]   MODERATOR VARIABLES - A CLARIFICATION OF CONCEPTUAL, ANALYTIC, AND PSYCHOMETRIC ISSUES [J].
ARNOLD, HJ .
ORGANIZATIONAL BEHAVIOR AND HUMAN PERFORMANCE, 1982, 29 (02) :143-174
[4]   DEVIL RIDES AGAIN - CORRELATION AS AN INDEX OF FIT [J].
BIRNBAUM, MH .
PSYCHOLOGICAL BULLETIN, 1973, 79 (04) :239-242
[5]   DEVILS ADVOCATES - DONT CONFOUND MODEL TESTING AND MEASUREMENT - REPLY [J].
BIRNBAUM, MH .
PSYCHOLOGICAL BULLETIN, 1974, 81 (11) :854-859
[7]   ANALYSIS OF MULTIPLICATIVE COMBINATION RULES WHEN THE CAUSAL VARIABLES ARE MEASURED WITH ERROR [J].
BUSEMEYER, JR ;
JONES, LE .
PSYCHOLOGICAL BULLETIN, 1983, 93 (03) :549-562
[8]   PARTIALED PRODUCTS ARE INTERACTIONS - PARTIALED POWERS ARE CURVE COMPONENTS [J].
COHEN, J .
PSYCHOLOGICAL BULLETIN, 1978, 85 (04) :858-866
[9]  
Cohen J., 1983, APPL MULTIPLE REGRES, P490
[10]  
COHEN JV, 1977, STATISTICAL POWER AN