*
chapter_9_table_1

The following data represent a pre-post design, where a training program designed to
assist people in losing weight is evaluated. An initial measure of weight is 
collected to use as a baseline measure (specifically as a covariate in the present 
analysis) and then randomly assign participants to one of two groups. At the end of 
the training program another measure of weight is obtained. The question of interest 
is: "did the participants who received the treatment lose more weight than those that 
were assigned to the wait-list control group?" 

As before, we will make use of the GLM procedure. The difference in the case of an
ANCOVA is that the effect of the covariate will be included on the right hand side of
the equals sign, as was the case previously with the grouping factor. The difference 
for covariates is that they are (generally) not classification variables but 
quantitative variables and are thus not included on the class line as grouping variables
generally are. Note that the /SOLUTION option is given on the model line. This is 
necessary in order for SAS to print the parameter estimates.

Note that the Type III sums of squares is what is generally of interest in this context, 
and it is these that are reported in the text.
;


LIBNAME md 'd:\data files by type\sas data files\tables';
     Data c9t1;
       SET md.chapter_9_table_1;
PROC GLM DATA=c9t1;
CLASS group;
MODEL y = x group / SOLUTION;
RUN;