Deviance explained by individual covariate

[Jane Reid]

Hi,

I'm running some analyses to look at the relationship between parent age and offspring survival (I have a long-term dataset with known age parents and encounter histories of offspring based on colour-ring resightings).

I have done this by modelling parent age as an individual covariate appended to the encounter history of each offspring. All works fine, and models that include linear and quadratic effects of parent age are strongly supported.

Now what I want to do is work out what proportion of deviance is explained by parent age. But I don't see how I can do this using ANODEV, since I don't have a suitable global model. For example, my situation is different from one where the covariate of interest is clearly a temporal variable (eg weather), where the deviance explained could be calculated by comparing the weather-constrained model with the fully time-dependent and time-independent basic models. The problem is that I can't fit a fully 'parent-dependent' model, since most parents only contribute a small number of offspring to the dataset, and it would be hideously over-parameterised.

I'd be very grateful for any suggestions as to whether and how it might be possible to calculate the proportion of deviance explained by an individual covariate (such as parent age) where I can't run what I imagine would be the most appropriate global model. I suppose this problem must exist for other individual covariates, such as body mass, where the most appropriate global model is not obvious either (at least to me)? Has anyone come across a solution?

Many thanks, Jane

[moses502]

I will be conducting a similar analysis. I find this paper cited often in these instances, I have yet to digest it so I am not sure if it is fully applicable. Perhaps it will be of help.

Skalski, J.R., A. Hoffmann, and S.G. Smith. 1993. Testing the significance of individual and cohort level covariates in animal survival studies. Pages 9-28 in J.D. Lebreton and P.M. North, editors. Marked Individuals in the Study of Bird Populations. Birkhauser-Verlag, Basel, Switzerland.

Also:

Altwegg, R., A. Roulin, M. Kestenholz, and L. Jenni. 2003. Variation and covariation in survival, dispersal, and population size in barn owls, Tyto alba. Journal of Animal Ecology. 72:391-399.[/i]