Factorial analysis of variance designs are often analyzed with multiple regression employing a matrix of coded variates. The use of dummy coded variates to test hypotheses about main effects can produce results that vary with the choice of dummy coding when certain types of hypotheses are tested. The problem is illustrated with an example data set and the nature of the problem is clarified.
Get full access to this article
View all access options for this article.
References
1.
AgrestiA.FinlayB. (1997) Statistical methods for the social sciences. (3rd ed.) Upper Saddle River, NJ: Prentice Hall.
2.
AppelbaumM. I.CramerE. M. (1974) Some problems in the nonorthogonal analysis of variance. Psychological Bulletin, 81, 335–343.
3.
CarlsonJ. E.TimmN. H. (1974) Analysis of nonorthogonal fixed-effects designs. Psychological Bulletin, 81, 563–570.
4.
CohenJ.CohenP. (1975) Applied multiple regression/correlation for the behavioral sciences. New York: Erlbaum.
5.
CramerE. M.AppelbaumM. I. (1980) Nonorthogonal analysis of variance—once again. Psychological Bulletin, 87, 51–57.
6.
HaysW. L. (1994) Statistics. (5th ed.) Fort Worth, TX: Harcourt Brace.
7.
HowellD. C. (1997) Statistical methods for psychology. (4th ed.) Belmont, CA: Duxbury.
8.
HowellO. C.McConaughyS. H. (1982) Nonorthogonal analysis of variance: Putting the question before the answer. Educational and Psychological Measurement, 42, 9–24.
9.
KeppelG.ZedeckS. (1989) Data analysis for research designs. New York: Freeman.
10.
KleinbaumD. G.KupperL. L.MullerK. E. (1988) Applied regression analysis and other multivariable methods. Boston, MA: PWS-KENT.
11.
LewisC.KerenG. (1977) You can't have your cake and eat it too: Some considerations of the error term. Psychological Bulletin, 84, 1150–1154.
12.
MarascuiloL. A.SerlinR. C. (1988) Statistical methods for the social and behavioral sciences. New York: Freeman.
13.
MyersJ. L.WellA. D. (1991) Research design & statistical analysis. New York: HarperCollins.
14.
O'BrienR. G. (1976) Comment on “Some problems in the nonorthogonal analysis of variance.”Psychological Bulletin, 83, 72–74.
15.
O'GradyK. E.MedoffD. R. (1988) Categorical variables in multiple regression: Some cautions. Multivariate Behavioral Research, 23, 243–260.
16.
OverallJ. E.LeeD. M.HornickC. W. (1981) Comparison of two strategies for analysis of variance in nonorthogonal designs. Psychological Bulletin, 90, 367–375.
17.
OverallJ. E.SpiegelD. K. (1969) Concerning least squares analysis of experimental data. Psychological Bulletin, 72, 311–322.
18.
OverallJ. E.SpiegelD. K.CohenJ. (1975) Equivalence of orthogonal and nonorthogonal analysis of variance. Psychological Bulletin, 82, 182–186.
19.
PedhazurE. J. (1997) Multiple regression in behavioral research. (3rd ed.) New York: Harcourt Brace.
20.
RawlingsR. R.Jr. (1972) Note on nonorthogonal analysis of variance. Psychological Bulletin, 77, 373–374.
21.
RawlingsR. R.Jr. (1973) Comments on the Overall and Spiegel paper. Psychological Bulletin, 79, 168–169.
