Study design: This is a cross-sectional survey study using multivariate ordered logitregression models.
2
A stepwise logitregression procedure was performed in order to determine the subset of measures which best distinguish ARMS subjects from HC.
3
HIV stigma was not found to be a significant predictor when binary logitregression was run with medication adherence at 1 year.
4
Our findings are tempered by a small sample size and lack of a direct relationship between stigma and adherence on binary logitregression analysis.
5
A logitregression was used to estimate the association between hospital characteristics (bed size, location, teaching status, ownership) and having any hospital-affiliated cessation program.
6
Ordered logitregressions were used to analyze variations across multiple subgroups.
7
Logitregression models were developed to estimate and compare prescription patterns in both countries.