Spotlights, Floodlights, and the Magic Number Zero: Simple Effects Tests in Moderated Regression

被引:1419
作者
Spiller, Stephen A. [1 ]
Fitzsimons, Gavan J. [2 ]
Lynch, John G., Jr. [3 ,4 ]
McClelland, Gary H. [5 ]
机构
[1] Univ Calif Los Angeles, Anderson Sch Management, Los Angeles, CA 90024 USA
[2] Duke Univ, Fuqua Sch Business, Durham, NC 27706 USA
[3] Univ Colorado, Leeds Sch Business, Boulder, CO 80309 USA
[4] Univ Colorado, Ctr Res Consumers Financial Decis Making, Boulder, CO 80309 USA
[5] Univ Colorado, Inst Cognit Sci, Boulder, CO 80309 USA
关键词
moderated regression; spotlight analysis; simple effects tests; NEGATIVE CONSEQUENCES; PROBING INTERACTIONS; DICHOTOMIZATION;
D O I
10.1509/jmr.12.0420
中图分类号
F [经济];
学科分类号
02 ;
摘要
It is common for researchers discovering a significant interaction of a measured variable X with a manipulated variable Z to examine simple effects of Z at different levels of X. These "spotlight" tests are often misunderstood even in the simplest cases, and it appears that consumer researchers are unsure how to extend them to more complex designs. The authors explain the general principles of spotlight tests, show that they rely on familiar regression techniques, and provide a tutorial demonstrating how to apply these tests across an array of experimental designs. Rather than following the common practice of reporting spotlight tests at one standard deviation above and below the mean of X, it is recommended that when X has focal values, researchers should report spotlight tests at those focal values. When X does not have focal values, it is recommended that researchers report ranges of significance using a version of Johnson and Neyman's test the authors term a "floodlight."
引用
收藏
页码:277 / 288
页数:12
相关论文
共 28 条
[1]  
Aiken LS., 1991, MULTIPLE REGRESSION
[2]   Arbitrary metrics in psychology [J].
Blanton, H ;
Jaccard, J .
AMERICAN PSYCHOLOGIST, 2006, 61 (01) :27-41
[3]   PARADIGM FOR DEVELOPING BETTER MEASURES OF MARKETING CONSTRUCTS [J].
CHURCHILL, GA .
JOURNAL OF MARKETING RESEARCH, 1979, 16 (01) :64-73
[4]   The Presence of Something or the Absence of Nothing: Increasing Theoretical Precision in Management Research [J].
Edwards, Jeffrey R. ;
Berry, James W. .
ORGANIZATIONAL RESEARCH METHODS, 2010, 13 (04) :668-689
[5]  
Fernbach Philip M., 2012, J CONSUM RES, V40, DOI [10.1086/667782, DOI 10.1086/667782J]
[6]   Cognitive reflection and decision making [J].
Frederick, S .
JOURNAL OF ECONOMIC PERSPECTIVES, 2005, 19 (04) :25-42
[7]  
Hayes A. F., 2012, CISC VIS NETW IND GL, DOI DOI 10.1094/PDIS-11-11-0999-PDN
[8]   Computational procedures for probing interactions in OLS and logistic regression: SPSS and SAS implementations [J].
Hayes, Andrew F. ;
Matthes, Joerg .
BEHAVIOR RESEARCH METHODS, 2009, 41 (03) :924-936
[9]   Negative consequences of dichotomizing continuous predictor variables [J].
Irwin, JR ;
McClelland, GH .
JOURNAL OF MARKETING RESEARCH, 2003, 40 (03) :366-371
[10]   Misleading heuristics and moderated multiple regression models [J].
Irwin, JR ;
McClelland, GH .
JOURNAL OF MARKETING RESEARCH, 2001, 38 (01) :100-109