About Anita2016

SteveDenham · ‎08-01-2016

I note that you have some non-estimable main effect LSmeans, so I am going to suggest the following, assuming the model is fit in PROC MIXED: proc mixed data=yourdataset; class treatment time subjectid; model response_variable=treatment*time; repeated time/subject=subjectid type=sp(pow)(t); lsmeans treatment*time; slice treatment*time / sliceby=time diff; run; Some things to note here. I see that your time points are not equally spaced. In yourdataset, define t=time, so that you will have a continous version of time to feed into the spatial power covariance structure. The key here is the SLICE statement. This should enable you to get differences between lsmeans for treatment at each time point where data exists for the treatments. At some points, only one treatment was measured, so no difference can be calculated. Steve Denham

SteveDenham · ‎06-28-2016

Repeated categorical measures are difficult to model, but could be done. If there is no reason to expect any odd distributions, a general logit multinomial model could be fit. If the OP has access to SAS/STAT14.1, I would strongly recommend looking at Example 43.6 GEE for Nominal Multinomial Data in the PROC GEE documentation. This example should get you started. A true correspondence analysis does not consider repeated measures, and so I would hesitate to go that route. You might start with the following untested code: proc gee data=yourdata; class animal treatment time activity; model activity=treatment/dist=multinomial link=glogit; repeated subject=animal / within=time; lsmeans treatment/diff means oddsratio cl; run; Steve Denham

Online Status	Offline
Date Last Visited	‎07-24-2016 01:55 PM

Re: ANOVA with repeated measures and correspondence analysis

Re: ANOVA with repeated measures and correspondence analysis

ANOVA with repeated measures and correspondence analysis

interpretation LS means

Re: interpretation LS means

Re: ANOVA with repeated measures and correspondence analysis