I'm trying to figure out the best statistical test to use to understand my data. I've searched but haven't found anything super applicable. I'm working with an endangered animal species and have a lot of measurements taken at the same time each year, and I'm trying to study growth. I'd like to know two main things: when this species reaches adult size (so stops growing), and whether there are differences between male and females at any ages. So basically trying to see if there's a significant difference between (for example) weight at age 4 and at age 5; if there's no difference, that should mean they stop growing at age 4.
I'll be doing the same test for lots of different measurements, e.g., weight, spine length, arm length, etc. I have repeat measures for some animals because some were measured at various ages (for example I have Zoe's weight at ages 1 and 2 years), but some animals were only measured once, so that has to be controlled for I'm sure. I don't have tons of data because this species is pretty endangered and has a low population size--usually around 5-12 measurements for each age group.
I've tried a bunch of things, but have been told by various people that they don't really work. In the beginning I was just comparing the means at each age (so a t test to compare the weight for males at age 1 vs their weight at age 2, etc., which is obviously too simplistic). I've tried mixed models, looking at marginal means of regressions, etc. but nothing seems to really be getting to the root of it. Especially because there is, for example, a significant difference between animal's weights between ages 3 and 5, but there's no difference between ages 3 and 4 or 4 and 5. So this means they are still growing, but if I just looked at the straight means, then they stop and start again.
I hope this was enough information to be helpful. Please let me know if you have any ideas! Below is my most recent attempt. I'm using R btw!
mod<-mixed(Weight~Sex+Age+Sex*Age+(1|ID), data = data)
emmeans(mod, list(pairwise ~ Age|Sex), adjust = "tukey")