I'm excited to share a preprint of my work identifying statistical methods for modeling butterfly populations in #ecology and #conservation. I developed guidelines for fitting sparse transect monitoring data with Generalized Additive Models (GAMs), based in large part on a new #Rstats package I developed to simulate and fit realistic butterfly data.

https://biorxiv.org/cgi/content/short/2023.12.07.570644v1

#rstats question for mgcv

If I want to test whether there is support for a smooth x factor effect, I can just include the smooth and the smooth x factor as separate terms to create nested models, right? As in

library(mgcv)
set.seed(0)
dat<-gamSim(5,n=200,scale=2)
##make explicit factor
dat$fac = factor(letters[dat$x0])

m = gam(y ~ s(x1) + fac + s(x1, by = fac), data = dat)
m1 = gam(y ~ s(x1) + fac, data = dat)
anova(m, m1, test = "F")

@noamross @gavinsimpson

#Rstats question:

I'm fitting some mixed models of the form

y ~ x + (1| category)

etc, where I have estimated uncertainty in y in the form of variance.

To carry out weighted regression (e.g. using lmer with `weights = SOMETHING`),
I want to weight by the inverse of the variance, right? Or is it the inverse of the standard deviation? These give pretty different answers!