Replies: 1 comment 3 replies
-
|
Questions are never redundant! To me, this does not look like a pattern. However, if you want to formally assess if the latent variable depends on a covariate, I suggest you have a look at this vignette: https://jenniniku.github.io/gllvm/articles/vignette6.html#:~:text=When%20including%20predictor%20variables%2C%20the,number%20of%20parameters%20to%20estimate. |
Beta Was this translation helpful? Give feedback.
3 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Hello,
I hope this Q is not redundant, but I am returning to this issue after some time and seem to still be struggling with it.
I’m exploring species co-occurrence and correlations and the effect of environmental variables on them (16 species, 1000 rows). I’ve already ran a basic GLLVM with no env. Variables included (model based on best AIC):
fit1lv <- gllvm(A, family =binomial(link="probit"), num.lv = 1, seed = 1234)
I want to see if the latent variables of this null model correspond to any of my 6 environmental covariates. These 6 covariates are already chosen from a bigger data set after removing correlated variables.
If I understand correctly, covariates that exhibit a trend with the LVs are a good pick for the actual GLLVM model that includes env. variables as a way to ensure I am not including covariates in the model that have no bearing on the species occurrence trends. Am I correct in that assumption?
The graphs I receive look like this:
(for (i in 1:length(colnames(B))) {
covariate <- B[,i]
rbPal <- colorRampPalette(c('red', 'blue'))
Colorsph <- rbPal(20)[as.numeric(cut(covariate, breaks = 20))]
breaks <- seq(min(covariate), max(covariate), length.out = 30)
ordiplot(fit1lv, main = paste0("Ordination of sites, color: ",colnames(B)[i]),
symbols = TRUE, s.colors = Colorsph, xlim = c(-1.2,1.2), ylim = (c(-1.2, 1.2)))
})
And I am not sure how to interpret this. Is there a trend showing in any of these (red being low values and blue high values).
Beta Was this translation helpful? Give feedback.
All reactions