Regression Analysis for Categorical Moderators

Herman Aguinis, Ph.D.
John F. Mee Chair of Management, Professor of Organizational Behavior & Human Resources, and Founding Director of the Institute for Global Organizational Effectiveness
Kelley School of Business, Indiana University

2004, 205 pages, hardcover

ISBN 978-1-57230-969-2, List price: $45.00

 

If you cannot see the applets on this page, please download the java plug-in here.
To automatically download the Java plug-in click here.

If the programs are blocked due to "security concerns" or "out of date" applets, click on the following link to read instructions on how to add exceptions to be able to run the programs:
RunningJava.pdf

 

Click here to read a review of this book published in International Journal of Consumer Studies (January 2005)

Click here to read a review of this book published in Organizational Research Methods (January 2005)

 


 

Resources

This Web page includes resources for the book Regression Analysis for Categorical Moderators by Herman Aguinis (2004, Guilford Press). In case of queries, feel free to email me at haguinis@indiana.edu

MULTIVAR

This program was used to create the data set for Chapter 3. The program is a multivariate random normal scores generator that uses the Box and Muller and Choleski Factorization algorithms. Click here to download the source code and executable versions of the program.

Source: Aguinis, H. (1994). A QuickBasic program for generating correlated multivariate random normal scores. Educational and Psychological Measurement, 54, 687-689. [click here to view article]

Pay for Performance Data Set for Chapter 3

Click here to download the data file described in Chapter 3. The data file is included in SPSS and excel formats.

ALTMMR

This program is described in Chapter 4. It checks whether the homogeneity of error variance assumption has been violated and conducts a test for moderation using analyses other than MMR when there is a violation of the assumption.

Click here to download the source code and executable versions of ALTMMR.

Source: Aguinis, H., Petersen, S. A., & Pierce, C. A. (1999). Appraisal of the homogeneity of error variance assumption and alternatives to multiple regression for estimating moderating effects of categorical variables. Organizational Research Methods, 2, 315-339. [click here to view article]

CAQ

This program is described in Chapter 6. It administers questionnaires on IBM and IBM-compatible personal computers by prompting respondents to indicate their answer by clicking on a graphic line segment displayed on the screen.

Click here to download the source code and executable versions of CAQ.

Source: Aguinis, H., Bommer, W. H., & Pierce, C. A. (1996). Improving the estimation of moderating effects by using computer-administered questionnaires. Educational and Psychological Measurement, 56, 1043-1047. [click here to view article]

POWER

This program is described in Chapter 7. It estimates the statistical power to detect a dichotomous moderator variable using moderated multiple regression (MMR). It computes power for specified conditions of effect size (i.e., absolute difference between subgroup correlation coefficients), total sample size, and sample sizes in moderator-based subgroups.

Click here to download the source code and executable versions of POWER.

Source: Aguinis, H., Pierce, C. A., & Stone-Romero, E. F. (1994). Estimating the power to detect dichotomous moderators with moderated multiple regression. Educational and Psychological Measurement, 54, 690-692.  [click here to view article]

MMRPWR

This program is described in Chapter 7. It estimates the statistical power to detect a dichotomous moderator variable with MMR specified conditions of effect size (i.e., absolute difference between subgroup correlation coefficients), total sample size, sample sizes in moderator-based subgroups, predictor-moderator intercorrelation, and predictor variable range restriction.

Click here to download the source code and executable versions of MMRPWR.

Source: Aguinis, H., & Pierce, C. A. (1998). Statistical power computations for detecting dichotomous moderator variables with moderated multiple regression. Educational and Psychological Measurement, 58, 668-676. [click here to view article]

MMRPOWER

This program is described in Chapter 7 and Chapter 8. It estimates statistical power using a theory-based approximation. It can be used for moderators with more than 2 levels.

Source: Aguinis, H., Boik, R.J., & Pierce, C.A. (2001). A generalized solution for approximating the power to detect effects of categorical moderator variables using multiple regression. Organizational Research Methods, 4, 291-323. [click here to view article]

f 2

This program computes the modified f 2 moderating effect size index described in Chapter 9. Click here to download the source code and executable versions of this program.

Source for Algorithm: Aguinis, H., Beaty, J. C., Boik, R. J., & Pierce, C. A. (2005). Effect size and power in assessing moderating effects of categorical variables using multiple regression: A 30-year review. Journal of Applied Psychology, 90, 94-107. [click here to view article]

Source for Program: Aguinis, H., & Pierce, C. A. (2006). Computation of effect size for moderating effects of categorical variables in multiple regression. Applied Psychological Measurement, 30, 440-442. [click here to view article]

 



  Herman Aguinis, Web: http://hermanaguinis.com

© Dr. Herman Aguinis. All rights reserved. All copyrights and trademarks acknowledged. This site was last edited on May 4, 2016.

I am thankful to Vara Allamaraju and Kevin Turner for their assistance with Java programming.