Diagnostics

Little’s MCAR Test [1]

Take the mean of the data with missing values and take the mean of the data without missing values. If they’re the same/simlar, then it’s more likely that your data is MCAR.

[1]Roderick J. A. Little. (1988). A Test of Missing Completely at Random for Multivariate Data with Missing Values. Journal of the American Statistical Association, 83(404), 1198-1202. doi:10.2307/2290157