From: A nonparametric multiple imputation approach for missing categorical data
 | Pr(Y=1)=0.297 | Pr(Y=2)=0.250 | ||||||
---|---|---|---|---|---|---|---|---|
Method | Est | SD | SE | CR | Est | SD | SE | CR |
FO | 0.298 | 0.023 | 0.023 | 0.952 | 0.249 | 0.021 | 0.022 | 0.974 |
CC | 0.322 | 0.032 | 0.033 | 0.910 | 0.303 | 0.033 | 0.032 | 0.606 |
 | Working models for Y: | Five covariates with logit link | ||||||
 |  | (misspecified scenario 3) | ||||||
 | Working models for δ: | Five covariates with logit link | ||||||
CE | 0.291 | 0.036 | 0.037 | 0.954 | 0.230 | 0.031 | 0.032 | 0.900 |
PMI | 0.307 | 0.033 | 0.033 | 0.942 | 0.271 | 0.034 | 0.033 | 0.902 |
NNMI MLR (5,0.4,0.4;0.2) | 0.301 | 0.033 | 0.033 | 0.940 | 0.260 | 0.031 | 0.032 | 0.942 |
NNMI MLR (5,0.1,0.7;0.2) | 0.302 | 0.034 | 0.034 | 0.946 | 0.259 | 0.032 | 0.032 | 0.936 |
NNMI MLR (5,0.7,0.1;0.2) | 0.301 | 0.032 | 0.033 | 0.944 | 0.260 | 0.033 | 0.032 | 0.930 |
NNMI CLR (5,0.4,0.4;0.2) | 0.299 | 0.033 | 0.033 | 0.936 | 0.263 | 0.032 | 0.033 | 0.936 |
NNMI CLR (5,0.1,0.7;0.2) | 0.297 | 0.033 | 0.033 | 0.930 | 0.263 | 0.033 | 0.033 | 0.926 |
NNMI CLR (5,0.7,0.1;0.2) | 0.302 | 0.032 | 0.034 | 0.948 | 0.261 | 0.032 | 0.032 | 0.942 |