Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: calcuating unadjusted and adjusted means

From   "Fitzmaurice, Ann E." <>
To   "" <>
Subject   st: calcuating unadjusted and adjusted means
Date   Sun, 15 May 2011 15:01:44 +0100

I  run a regression and want to calculate the unadjusted and adjusted means of the sample included in the regression

I run the following where the variable bir_grp has four categories  was entered in the regression as i.bir_grp2 (sample_mod5 has previously been calculated)
Regress ............
predict xb
rename xb pred_m5
 mean pred_m5 if sample_mod5 ==1 , over (bir_grp2)

 adjust if sample_mod5==1, by (bir_grp2)

after this command I get an error message " variable miscbirth not found"

mean babywt2  if sample_mod5==1 ,over (bir_grp2)

This gives means  for the four groups which are identical between the two methods that work , but the confidence intervals are different,

Can  anyone advise how to calculate the group means before and after regression



Ann E Fitzmaurice

The University of Aberdeen is a charity registered in Scotland, No SC013683.

*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index