Using SPSS MANOVA to fit a within subjects ANCOVA with a constant covariate
It is assumed in this example we have a covariate with identical responses within subject (x1, x2) and a repeated measures factor of 2 levels (y1, y2). This approach effectively follows Winer(1971), p.803 and omits any terms the covariate by factor interaction from the within subjects portion of the ANCOVA.
In general an identical covariate column may be generated using the COMPUTE statement in SPSS.
COMPUTE x2 = X1.
* as recommended in SPSS resolution 22133 data list free /y1 y2 x1 x2. begin data. 2 5 2 2 2 4 1 1 3 2 2 2 4 3 3 3 2 4 4 4 3 5 5 5 4 6 6 6 5 7 7 7 end data. manova y1 y2 with x1 x2 /wsfactors time(2) /contrast(time)=polynomial /wsdesign /print=transform signif(univ).