Regression Analysis for Categorical Moderators

Note: Supplemental materials are not guaranteed with Rental or Used book purchases.

ISBN: 9781572309692 | 1572309695
Cover: Hardcover
Copyright: 12/23/2003

Rent

(Recommended)

$42.30

Term

Due

Price

Semester

Aug 2

$42.30

Quarter

Jul 19

$40.19

Short Term

Jun 21

$38.07

*This item is part of an exclusive publisher rental program and requires an additional convenience fee. This fee will be reflected in the shopping cart.
Buy Used

Usually Ships in 2-4 Business Days

$43.12
Buy New

Usually Ships in 3-5 Business Days

$57.80

Have you ever wondered if birth order effects vary across ethnic groups? Whether a particular clinical intervention is likely to yield dissimilar outcomes for men and women? Or if the effectiveness of a sales promotion is dependent on a market segment? Questions like these can be effectively answered by using a statistical tool known as moderated multiple regression (MMR). This book provides practical guidance for using MMR to better assess whether the relationship between two quantitative variables is moderated by group membership. Included are discussions and fully worked-out examples of how to conduct and interpret MMR analysis, as well as descriptions of computer programs that allow investigators to check whether their MMR test for moderation can be trusted. Using examples from a variety of different disciplines--from psychology and education to management and political science--Herman Aguinis first shows readers how to distinguish between moderated and mediated

What Is a Moderator Variable and Why Should We Care?	p. 1
Why Should We Study Moderator Variables?	p. 3
Distinction between Moderator and Mediator Variables	p. 5
Importance of A Priori Rationale in Investigating Moderating Effects	p. 7
Conclusions	p. 8
Moderated Multiple Regression	p. 10
What Is MMR?	p. 10
Endorsement of MMR as an Appropriate Technique	p. 16
Pervasive Use of MMR in the Social Sciences: Literature Review	p. 18
Conclusions	p. 20
Performing and Interpreting Moderated Multiple Regression Analyses Using Computer Programs	p. 22
Research Scenario	p. 23
Data Set	p. 24
Conducting an MMR Analysis Using Computer Programs: Two Steps	p. 26
Computation of Product Term	p. 26
Computation of Regression Equations	p. 28
Output Interpretation	p. 31
Interpretation of Model 1	p. 31
Interpretation of Model 2	p. 33
Additional Issues in Output Interpretation	p. 35
Conclusions	p. 39
The Homogeneity of Error Variance Assumption	p. 42
What Is the Homogeneity of Error Variance Assumption?	p. 42
Two Distinct Assumptions: Homoscedasticity and Homogeneity of Error Variance	p. 44
Is It a Big Deal to Violate the Assumption?	p. 47
Violation of the Homogeneity of Error Variance Assumption: Type I Error Rates	p. 48
Violation of the Homogeneity of Error Variance Assumption: Type II Error Rates	p. 50
Violation of the Assumption in Published Research	p. 51
How to Check Whether the Homogeneity Assumption Is Violated	p. 54
What to Do When the Homogeneity of Error Variance Assumption Is Violated	p. 56
ALTMMR: Computer Program to Check Assumption Compliance and Compute Alternative Statistics If Needed	p. 58
Program Description	p. 59
Input	p. 60
Assessment of Variance Heterogeneity	p. 60
Computation of Alternatives to MMR	p. 61
Output	p. 61
Conclusions	p. 63
MMR's Low-Power Problem	p. 65
Statistical Inferences and Power	p. 65
Controversy over Null Hypothesis Significance Testing	p. 67
Purpose of NHST	p. 67
Meaning of NHST	p. 67
Controversy over NHST: A Human Factors Problem	p. 68
Factors Affecting the Power of All Inferential Tests	p. 69
Factors Affecting the Power of MMR	p. 70
Variable Distributions	p. 70
Predictor Variable Variance Reduction	p. 70
Transformations of Skewed Criterion Scores	p. 71
Operationalization of Criterion and Predictor Variables	p. 72
Measurement Error	p. 73
Scale Coarseness	p. 74
Polichotomization of a Truly Continuous Variable	p. 75
Sample Size	p. 75
Total Sample Size	p. 75
Sample Size Across Moderator-Based Subgroups	p. 76
Characteristics of the Predictor Variables	p. 77
Correlation Between the Predictor X and the Moderator Z	p. 77
Correlation Between the Predictor X and the Criterion Y	p. 77
Interactive Effects	p. 78
Effect Sizes and Power in Published Research	p. 78
Implications of Small Observed Effect Sizes for Social Science Research	p. 80
Conclusions	p. 82
Light at the End of the Tunnel: How to Solve the Low-Power Problem	p. 85
How to Minimize the Impact of Factors Affecting the Power of All Inferential Tests	p. 86
Sample Size	p. 86
Preset Type I Error Rate	p. 86
Moderating-Effect Size	p. 88
How to Minimize the Impact of Factors Affecting the Power of MMR	p. 88
Reduction of Variance in Predictor Variables	p. 88
Transformations of Skewed Criterion Scores	p. 89
Measurement Error	p. 90
Scale Coarseness	p. 90
Polichotomization of Truly Continuous Variables	p. 92
Total Sample Size	p. 93
Sample Size across Moderator-Based Subgroups	p. 93
Correlation between the Predictor X and the Moderator Z	p. 94
Correlation between the Predictor X and the Criterion Y	p. 94
Conclusions	p. 94
Computing Statistical Power	p. 97
Usefulness of Computing Statistical Power	p. 97
Empirically Based Programs	p. 100
Program POWER	p. 100
Specifications	p. 100
Example	p. 101
Limitations	p. 101
Program MMRPWR	p. 103
Specifications	p. 103
Example	p. 104
Limitations	p. 106
Theory-Based Program	p. 107
Program MMRPOWER	p. 107
Specifications	p. 108
Example	p. 110
Limitations	p. 110
Relative Impact of the Factors Affecting Power	p. 113
Conclusions	p. 115
Complex MMR Models	p. 117
MMR Analyses Including a Moderator Variable with More Than Two Levels	p. 118
Dummy Coding	p. 119
Unweighted Effect Coding	p. 121
Weighted Effect Coding	p. 122
Contrast Coding	p. 123
How to Choose a Coding Scheme: The Importance of Theory	p. 124
Computing Statistical Power	p. 125
Linear Interactions and Nonlinear Effects: Friends or Foes?	p. 126
Testing and Interpreting Three-way and Higher-Order Interaction Effects	p. 131
Examining "Targeted" Lower-Order Interactions	p. 134
Conclusions	p. 135
Further Issues in the Interpretation of Moderating Effects	p. 138
Is the Moderating Effect Practically Significant?	p. 139
Measures of Improved Fit	p. 139
Difference in Correlations Across Moderator-Based Subgroups	p. 139
Proportion of Variance Explained by the Moderating Effect as Indexed by R[superscript 2]	p. 140
Proportion of Variance Explained by the Moderating Effect as Indexed by f[superscript 2]	p. 141
Proportion of Variance Explained by the Moderating Effect as Indexed by Modified f[superscript 2]	p. 141
Measures of Improved Prediction	p. 143
Differences in Unstandardized Regression Coefficients Across Moderator-Based Subgroups	p. 143
Standardized Effect of the Moderator on the Y on X Slope	p. 144
Differential Impact of the Moderator at Various Values of the Predictor X	p. 146
The Signed Coefficient Rule for Interpreting Moderating Effects	p. 149
The Importance of Identifying Criterion and Predictor A Priori	p. 150
Conclusions	p. 152
Summary and Conclusions	p. 155
Moderators and Social Science Theory and Practice	p. 155
Use of Moderated Multiple Regression	p. 156
Homogeneity of Error Variance Assumption	p. 159
Low Statistical Power and Proposed Remedies	p. 159
More Complex MMR Models	p. 162
Assessing Practical Significance	p. 162
Conclusions	p. 164
Computation of Bartlett's (1937) M Statistic	p. 167
Computation of James's (1951) J Statistic	p. 168
Computation of Alexander's (Alexander & Govern, 1994) A Statistic	p. 170
Computation of Modified f[superscript 2]	p. 171
Theory-Based Power Approximation	p. 173
References	p. 175
Author Index	p. 190
Subject Index	p. 194
Table of Contents provided by Rittenhouse. All Rights Reserved.

Please wait while the item is added to your bag...

FREE SHIPPING

Amazon no longer offers textbook rentals. We do!

Regression Analysis for Categorical Moderators

Summary

Author Biography

Table of Contents

Supplemental Materials