Details
-
Sub-task
-
Status: Open
-
Major
-
Resolution: Unresolved
-
None
-
None
-
None
Description
This builtin will take a dataset with missing values as input and will infer if the data is Missing Completely at Random (MCAR), Missing at Random (MAR) or Not Missing at Random (NMAR).
For MCAR a uniformity test could be done to find if the missing values are uniformly distributed.
MAR could be identified by finding the functionally dependent attributed and seeing if the missing values are dependent on other columns
MNAR is a tricky case and one way to see it is that if missingness is not MCAR and MAR then it is MNAR.