extensions - Allow for analysis of groups of populations with shared interannual variation

[sebdalgarno]

The contractor will extend the bboutools survival, recruitment, and population growth models to allow for analysis of groups of populations. The extended models will assume that the distribution of interannual variation does not differ among populations, while allowing for variation in intercepts and trends among populations

[sebdalgarno]

does each population need to have the same years?

[sebdalgarno]

if allow different year combos, then missing combos are treated as latent random effects and the posterior will basically be drawn from the prior and have no likelihood contribution. this is fine as long as user understands how to interpret this

in predictions or plots, could only show observed combinations - option to user? or standard?

[sebdalgarno]

currently not allowed for ML fits - is this necessary? client only interested in Bayesian implementation