The HPPLS Procedure

Observations that have any missing independent variables (including all classification variables) are excluded from the analysis, and no predictions are computed for such observations. Observations that have no missing independent variables but do have missing dependent variables are also excluded from the analysis, but predictions are computed. If you use the PARTITION statement and specify the ROLEVAR= option, observations that contain the missing ROLEVAR= variable are excluded from the analysis, but predictions are computed for them.