skip to main content skip to footer

Assignment of Treatment Group on the Basis of a Covariate ANCOVA

Rubin, Donald B.
Publication Year:
Report Number:
ETS Research Bulletin
Document Type:
Page Count:
Subject/Key Words:
Analysis of Covariance (ANCOVA), Computer Software, Data Analysis, Sampling, Statistical Bias


When assignment to treatment group is made solely on the basis of the value of a covariate, X, effort should be concentrated on estimating the conditional expectations of the dependent variable Y given X in the treatment and control groups. One then averages the difference between these conditional expectations over the distribution of X in the relevant population. There is no need for concern about "other" sources of bias, e.g., unreliability of X, unmeasured background variables. If the conditional expectations are parallel and linear, the proper regression adjustment is the simple covariance adjustment. However, since the resulting estimates may be somewhat sensitive to the adequacy of the underlying model, it is wise to search for non-parallelism and non-linearity in these conditional expectations. Blocking on the values of X is also appropriate, although the resulting estimates may be somewhat sensitive to the coarseness of the blocking employed. (22pp.)

Read More