Artificial data story

Last edited on 27th April, 2004 by gs/ gs . - Host home page:
A small artificial data set to illustrate calculations for analysis of covariance.
The question is whether the response variable Y has different dsistribution in two groups. Besides a possible group effect, the response variable may be influenced by a covariable X.

N=6 observations
K=2 groups (treatment and control)
Response Y

J=1 regressor variable X

Scatterplot of response versus regressor, by group

Data file:
Source: D. Quade: Nonparametric Analysis of Covariance by Matching. Biometrics 28 (1982) 567-611.