O'Reilly logo

Practical Predictive Analytics by Ralph Winters

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Testing for MCAR

When you suspect that your data is MCAR, there are various statistical tests can help you determine if MCAR may be occurring. One important test is the Little test, which we will now run on the test missing value dataset.

First, install the BaylorEdPsych package, which contains the LittleMCAR test:

try(require(BaylorEdPsych) || install.packages("BaylorEdPsych",dependencies=TRUE)) library(BaylorEdPsych) 

Now, run the LittleMCAR test:

test_mcar<-LittleMCAR(all.df)  

Print the missing values found by the test. 4% of the data was found to be missing. This makes perfect sense, since 5% of the 1,000 males and 3% of the 1,000 females were generated with NAs.

print(test_mcar$amount.missing) print(test_mcar$p.value) 

Print the ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required