parameters::model_parameters appears to use the wrong degrees of freedom to compute p values in this model, which results in an overly conservative test:
library(parameters)
library(fixest)
library(carData)
d <- Greene
d$dv <- ifelse(Greene$decision == 'yes', 1, 0)
mod <- feglm(dv ~ language | judge,
data = d,
cluster = c('judge'), family = 'logit')
# many degrees of freedom
insight::get_df(mod)
# [1] 382
# normal and t give pretty similar results
pnorm(-2.48139) * 2
# [1] 0.01308711
pt(-2.48139, df = insight::get_df(mod)) * 2
# [1] 0.0135165
# but parameters::model_parameters uses 9 DF
pt(-2.48139, df = 9) * 2
# [1] 0.03491173
model_parameters(mod)
# # Fixed Effects
#
# Parameter | Log-Odds | SE | 95% CI | z | df | p
# -------------------------------------------------------------------------
# language [French] | -0.68 | 0.28 | [-1.31, -0.06] | -2.48 | 9 | 0.035
#
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4