Rerunning the Analysis for Little's MCAR Test

Figure 1. Missing Value Analysis dialog box
The Missing Value Analysis main dialog box. MaritalStatus, EducationalLevel, RetirementStatus, and Gender are selected as categorical variables. The rest are selected as quantitative variables.
  1. Recall the Missing Value Analysis dialog box.
  2. Click EM.
  3. Click OK.
Figure 2. EM means table
The EM Means table produced by Missing Value Analysis.

The results of Little's MCAR test appear in footnotes to each EM estimate table. The null hypothesis for Little's MCAR test is that the data are missing completely at random (MCAR). Data are MCAR when the pattern of missing values does not depend on the data values. Because the significance value is less than 0.05 in our example, we can conclude that the data are not missing completely at random. This confirms the conclusion we drew from the descriptive statistics and tabulated patterns.

At this point, because the data are not missing completely at random, it is not safe to listwise delete cases with missing values or singly impute missing values. However, you can use multiple imputation to further analyze this dataset.