Missing Data Patterns

The SURVEYIMPUTE procedure displays the missing data patterns in groups in a "Missing Data Patterns" table; the groups are based on whether the analysis variables are observed or missing. The input data set does not need to be sorted in any order.

For example, when a data set contains variables $Z_{1}$, $Z_{2}$, and $Z_{3}$ (in that order), up to eight groups of observations can be formed from the data set. Figure 110.7 displays the eight groups of observations and an unique missing pattern for each group.

Figure 110.7: Missing Data Patterns

Missing Data Patterns

Group Z1 Z2 Z3
1 X X X
2 X X .
3 X . X
4 X . .
5 . X X
6 . X .
7 . . X
8 . . .

An "X" in Figure 110.7 means that the variable is observed, and a "." means that the variable is missing.

The order of the groups is determined by the order in which you list the variables in the VAR statement. If you specify a different order of variables in the VAR statement, then the results are different even if the other specifications remain the same.