Comparison of techniques for handling missing covariate data within prognostic modelling studies: a simulation study.

However, the binary covariate X 5 and the dummy variable for X 8 representing group 3 (>30 mm) became borderline significant with increasing amounts of missingness.

also in 11,409 other papers

The likelihood ratio statistic remained highly significant for all missing data methods and levels of missingness (Figure 6a ).

also in 132,142 other papers