First you should choose any animal model like Insect or little mammal etc

second thing you have to choose many replicas of 2 groups i.e. one for light or small body sized and another bigger or heavy body sized

Now let them mate and wait for neonates...but before neotates emerge you try to get idea about optimum requirements of both i.e. bigger and smaller sized groups

Now after neonates getting make groups of bigger sized and smaller size and provide them optimum requirements

Note down all survival and no of day finally u will have a life table of both sized groups......

Hi Albert,

does this example fit to your question? They used a combination of state and time-varying covariate (serological measure). It allows for absence of measurement event if an individual is captured.Article Estimating transitions between states using measurements wit...

Another possibility is to use as many individual covariates as the number of occasion and to include it in your model in E-SURGE i+t*xind(1_t)

you can try to ask also on https://groups.google.com/forum/#!forum/esurge_ucare

Hope it helps,

Guillaume

Thanks Guillaume. In my case, I splitted a long dataset in several shorter periods and used CJS models to look at body size effects on survival within each period (I related body size measures taken at the beggining of the period to survival during the entire period). I am now preparing a response letter to the referees justifiying this "data splitting" approach, which has been used by other authors in the past (i.e. Carlson et al, 2008), but wanted to know about other alternative approaches. Thanks again for your response and the links!