I am studying seasonal changes in abundance of a fish species along a disturbance gradient. I sampled three locations at four seasons. My sampling sites at each location were very heterogeneous and the overall data was overdispersed . I am planning to analyze data using a GLMM with zero inflated model, considering LOCATION as a fixed factor and sampling site as a random factor. Should I also consider SEASON as a random factor (due to probable autocorrelation) or just nest it within LOCATION?
Slightly different from your proposals, but if you take season as a sequence (in time), you might use repeated measures for your analysis. See the WIKI page for some more info (or use your favourite search engine that will lead you to commercial pages).
https://en.wikipedia.org/wiki/Repeated_measures_design
Dear Michel,
Thank you very much for your answer. I have actually tried rmANOVA but the problem is that I am using count data that is non-normal and normality could not be achieved.
Yes if you use Season as a confounding variable, then I would apply repeeated measure model. If you are interested in differences among seasons you need to add it as a fixed effect. Using it as random effect answers you the question if there is a difference between sites "averaging out" the season effect, and the random estimate gives you an idea how much variance in the data is related to season.
Thank you. I am actually interested in differences among seasons but the data are highly correlated across seasons and I am not sure about using season as a fixed effect.
- Badges
- Science topic
- Similar topics
- Medicine
- Physiology
- Biosignals
- Biomedical Signal Processing
- Statistical Analysis