*
chapter_9_table_11

The question of interest in the present situation assumes that there are three blocks of 
elderly participants, six per block. The elderly participants are sorted into the three 
blocks as a function of their age. The purpose of the study was to assess the effect of 
age on motor control, measured by the number of errors on a certain task (where there 
were three tasks). 

The following syntax is used to replicate the results given in Table 9.12. The first
GLM statement corresponds to the randomized block design, the second GLM statement
corresponds to the ANOVA design, and the third GLM statement corresponds to the 
ANCOVA (where x is used as a covariate) design. Note that for the ANCOVA we will, as 
usual, make use of the Type III sums of squares (even though by default SAS also
prints the Type I sums of squares).
;

LIBNAME md 'd:\data files by type\sas data files\tables';
     Data c9t11;
       SET md.chapter_9_table_11;
title 'Randomized Block Design';
PROC GLM DATA=c9t11;
CLASS block task;
MODEL y = task block task*block;
RUN;
title 'ANOVA';
PROC GLM DATA=c9t11;
CLASS task;
MODEL y = task;
RUN;
title 'ANCOVA';
PROC GLM DATA=c9t11;
CLASS task;
MODEL y = task x;
RUN;