What could be a best analytic procedure to measure effect of walking program on activity level measured in terms of ordinal scale.
The activity level was measured 3 times (baseline, after intervnetion and after a month of intervnetion)
I guess repeated measures linear model will not be enough since people were coming and going out of the program, and there are missing data for drop-outs.
advice won't be definitive. personally i wouldn't be fixated on the 'repeated measures', you have 2 timepoints, the baseline is a baseline. If not for the missing data do proportional odds modelling (proc logistic, beware: https://digitalcommons.wayne.edu/cgi/viewcontent.cgi?article=1076&context=jmasm) at the primary timepoint. Could consider last-observation-carried-foward, although probably not because it couldn't be considered conservative in this scenario (assuming the primary timepoint is the last timepoint). Other options depend on the extent of drop out etc etc.
ANOVA, or Analysis Of Variance, is used to compare the averages or means of two or more populations to better understand how they differ. Watch this tutorial for more.