st: Predicted Odds Following Logistic Regression

[Melissa King <melissakng@gmail.com>]

This is a question regarding commands for displaying predicted odds
following logistic regression.

I am using logistic regression to estimate how about ten independent
variables, including four different medical services, impact a
person’s odds of hospital admission. Some of the medical services turn
out to have a strong and statistically significant impact on hospital
admission. For example, the odds ratio estimated for SERVICE1 is
0.044, which I interpret as meaning that those who receive SERVICE1
have a 96 percent decrease in odds of hospital admission.

After running the logistic regression, I used – adjust – to display
the predicted odds of inpatient admission for SERVICE1:

adjust, by (SERVICE1) exp

The following results are returned:

SERVICE1
0 = 1.29
1 = .48

Based upon the predicted odds returned by adjust, switching from
SERVICE1 = 0 to SERVICE1 = 1 does not appear to result in a 96 percent
decrease in odds of hospital admission. The decrease in odds appears
to be far less.

In the Stata Journal article “predict and adjust with logistic
regression” (2007), Maarten Buis pointed out that – adjust – will
return predictions for people with SERVICE1 = 1 who have average
values on all of the other independent variables. Could anyone confirm
whether this is why the decrease in odds resulting from a switch from
SERVICE1 = 0 to SERVICE1 = 1 predicted by – adjust – does not match
the decrease estimated by my logistic regression model? In other
words, do the odds ratios estimated by my logistic regression model
represent the average for people who receive SERVICE1, whereas the
predicted odds returned by – adjust – represent people who receive
SERVICE1 and who have average values on all the other independent
variables?

I apologize if this question is very basic. Not only am I a new Stata
user, but this is my first time running a logistic regression!  Thank
you for your time and assistance.

Melissa

-- 
Melissa King
www.realhealthpolicy.com

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/