Five distribution-free alternatives to parametric analysis of covariance are presented and
demonstrated using a specific data example. The results of simulation studies investigating
these procedures regarding their respective Type I error rate under a null condition and
their statistical power are also reviewed. The results indicate that the nonparametric
procedures have appropriate Type I error rates only for those situations in which para
metric A NCO VA is robust to violations of data assumptions. In terms of statistical power,
nonparametric alternatives to parametric ANCOVA provide a considerable power advan
tage only for situations in which extreme violations of assumptions have occurred and the
linear relationship between measures is weak.
Get full access to this article
View all access options for this article.
References
1.
Abunnaja, S.S. (1983) "The robustness of parametric and nonparametric analysis of covariance against unequal regression slopes and non-normality ." Presented at the meeting of the American Educational Research Association in Montreal, Canada.
2.
Bennett, B.M. (1968) "Rank-order tests of linear hypotheses."J. of Stat . Society B30: 483-489.
3.
Blai R.C. (1981) "A reaction to 'Consequences of failure to meet assumptions underlying the fixed effects analysis of variance and covariance ."' Rev. of Educ. Research51: 499-508.
4.
---and J. Higgins (1980) "A comparison of the power of Wilcoxon's rank-sum statistic to that of Student's t statistic under various non-normal distributions ." J. of Educ. Statistics5: 309-335.
5.
Burnett, T.D. and D.R. Barr (1977) "A nonparametric analogy of analysis of covariance ." Educ. and Psych. Measurement37: 341-348.
6.
Campbell, D.T. and J.C. Stanley (1963) Experimental and Quasi-Experimental Designs for Research. Chicago: Rand McNally .
7.
Conover, W.J. and R.L. Iman (1982) "Analysis of covariance using the rank transformation ." Biometrics38: 715-724.
8.
Elashoff, J.D. (1969) "Analysis of covariance: A delicate instrument " Amer. Educ. Research J.6: 383-401.
9.
Glass, G.U., P.D. Peckham, and J.R. Sanders (1972) "Consequences of failure to meet assumptions underlying the fixed effects analysis of variance and covariance." Rev. of Educ. Research42: 237-288.
10.
Hamilton, B.L. (1976) "A monte-carlo test of robustness of parametric and nonparametric analysis of covariance against unequal regression slopes ." J. of the Amer. Stat. Assn.71: 864-869.
11.
Hsu, T. ( 1983) "The robustness of ANCOVA to the violation of various assumptions: A review of recent studies." Presented at the meeting of the American Educational Research Association in Montreal , Canada.
12.
Marascuilo, L.A. and M. McSweeney (1977) Nonparametric and Distribution-Free Methods for the Social Sciences. Monterey, CA: Brooks/ Cole.
13.
McSweeney, M. and A.C. Porter (1971) "Small sample properties of nonparametric index of response and rank analysis of covariance." Occasional paper No. 16, Office of Research Consultation. Michigan State University, East Lansing, Michigan.
14.
Noether, G.E. (1967) Elements of Nonparametric Statistics. New York: John Wiley.
15.
Olejnik, S.F. and J. Algina (1983) "Parametric ANCOVA vs. rank transform ANCOVA when assumptions of conditional normality and homoscedasticity are violated." Presented at the meeting of the American Educational Research Association in Montreal, Canada.
16.
———and A.F. Abdel-Fattah ( 1984) "An analysis of statistical power curves for parametric ANCOVA and rank transform ANCOVA." Presented at the meeting of the American Educational Research Association, New Orleans, Louisiana.
17.
Porter, A.C. and M. McSweeney (1974) "Comparison of three common experimental designs to improve statistical power when data violate parametric assumptions." Presented at the meeting of the American Educational Research Association.
18.
Pratt, J.W. (1964) "Robustness of some procedures for the two-sample location problem." Amer. Stat. Assn. J.59: 665-678.
19.
Puri, M.L. and P.K. Sen (1969) "Analysis of covariance based on general rank scores ." Annals of Mathematical Statistics40: 610-618.
20.
Quade, D. (1967) "Rank analysis of covariance."J. of the Amer. Stat. Assn.62: 1187-1200.
21.
Rogosa, D. (1980) "Comparing nonparallel regression lines." Psych. Bul.88: 307-321.
22.
Seaman, S., J. Algina, and S.F. Olejnik (1984) "Type I probabilities and power of the rank and parametric ANCOVA procedures." Presented at the meeting of the American Educational Research Association, New Orleans, Louisiana.
23.
Shields, J.L. (1978) "An empirical investigation of the effect of heteroscedasticity and heterogeneity of variance on the analysis of covariance and the Johnson-Neyman technique." Technical paper 292, U.S. Army Research Institute for the Behavioral and Social Sciences, Alexandria, Virginia.
24.
Shirley, E.A. (1981) "A distribution-free method for analysis of covariance based on ranked data. J. of Applied Statistics30: 158-162.
