I've generated a very simple multilevel ordinal model using HLM software and
using the clmm function from the ordinal package in R. The threshold values and
coefficients are comparable, however the signs for the coefficients (and only
the coefficients; not the thresholds) are opposite (e.g., positive in HLM,
negative in clmm). This then impacts the odds ratios for the predictors. HLM
reports odds greater than one and clmm reports odds less than one. I
anticipate there is a very easy reason for what's happening, and it's just
escaping me. Can someone please advise on what I've overlooked?
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
