Compare subset to full sample

[Anne Todd]

Given the data structure below, how could I compare the mean of group==1 to the entire dataset (as opposed to comparing only to group==0)? Basically, I'm curious what the most efficient method would be to do ttest score, by(group) but with the full dataset as one of the groups.

* Example generated by -dataex-. For more info, type help dataex
clear
input byte(group score)
1 2
1 3
1 2
1 4
1 5
1 2
0 3
0 4
0 5
0 3
0 2
0 9
0 1
0 2
0 4
0 3
0 2
0 2
0 2
0 1
0 2
0 1
end

[Nick Cox]

You could go

tab group, su(score)

which would show group means and overall mean

EDIT: Too hasty an answer. Please see answer from Maarten Buis at #3

[Maarten Buis]

what you want is sometimes called effect coding. In Stata you can do this in two steps:

//step 1
reg score i.group

//step 2
contrast gw.group