ERIC Number: ED191867
Record Type: RIE
Publication Date: 1979-Nov
Reference Count: 0
The Care and Feeding of ANCOVA.
McLean, James E.
Recent research findings concerning analysis of covariance (ANCOVA) are reviewed, its use is illustrated, and a method for performing it using the Statistical Package for the Social Sciences is presented. In addition, methods for examining Elashoff's seven assumptions as a prerequisite to the correct application of ANCOVA are discussed. Specifically, the assumptions are: (1) that cases are assigned randomly to treatment conditions; (2) that the covariate is independent of the treatment effect; (3) that the covariate is measured without error; (4) that the covariate is linearly related to the dependent variable; (5) that the regression of the dependent variable on the covariate is the same for each group; (6) that for each level of the covariate, the dependent variable is normally distributed; (7) that the variance of the dependent variable at a given value of the covariate is constant across treatment groups and is independent of the covariate. ANCOVA can be performed very easily when the assumptions are kept in mind from the onset, but if one or more of the critical assumptions are not met, alternative types of analysis should be considered. (RL)
Publication Type: Reports - Evaluative; Speeches/Meeting Papers
Education Level: N/A
Authoring Institution: N/A
Identifiers: Statistical Package for the Social Sciences
Note: Paper presented at the Annual Meeting of the Mid-South Educational Research Association (Little Rock, AK, November, 1979). Best copy available.