Dropping values in Stata

Dropping values in Stata is achieved by the drop command. Let's load the auto training dataset and create a new variable:

gen my_car = 0
tab my_car

That's just a new variable with the value 0 for all observations in the dataset. Not very useful, so let's drop it:

drop my_car

Another use case would be dropping missing values. The rep78 (repair records from 1978), for instance has some missing values in it:

misstable summarize

We can see that the variable rep78 has 5 missing values in it (denoted by .). Let's drop these:

drop if rep78 == .

Now we can see that the missing values were dropped from the variable.