Analysis of Covariance (ANCOVA)

Analysis of covariance (ANCOVA) is a statistical model introduced by Sir Ronald Fisher that combines features of analysis of variance (ANOVA) with those of regression analysis. The purpose of ANCOVA is to examine differences between levels of one or more grouping variables on an outcome measure after controlling for variation or differences between populations on one or more nuisance variables. The grouping variable often represents different treatments, the outcome measure is the consequence of those treatments, and the nuisance variable either obscures true treatment differences or is a confounding variable that offers an alternative explanation for differences on the outcome other than the treatments.

The ANCOVA model is often underused in experimental research and misinterpreted in quasi-experimental studies. Researchers may not recognize the benefit of using ...