Skip to main content
9 events
when toggle format what by license comment
Nov 1, 2023 at 15:35 history edited Barton CC BY-SA 4.0
deleted 44 characters in body
Oct 26, 2023 at 10:07 history edited Barton CC BY-SA 4.0
added 44 characters in body
Oct 26, 2023 at 10:04 comment added Barton When I generate Poisson count variables, I fit them using Poisson regression (no overdispersion inherent in data). Removing a known significant covariate clearly has an impact on all fronts. Conversely, when NB2 count variables are generated and fit using NB2 regression, this effect is not observed - except in LL values.
Oct 26, 2023 at 9:27 comment added dimitriy Could this be because NB requires that the NB distribution be fully correct, including a specific variance/mean relationship, while the Poisson quasi-MLE doesn’t?
Oct 26, 2023 at 8:40 history edited Barton CC BY-SA 4.0
deleted 22 characters in body
Oct 25, 2023 at 19:21 answer added Peter Flom timeline score: 1
Oct 25, 2023 at 13:53 history edited Barton CC BY-SA 4.0
edited title
S Oct 25, 2023 at 13:52 review First questions
Oct 25, 2023 at 15:11
S Oct 25, 2023 at 13:52 history asked Barton CC BY-SA 4.0