# st: Logistic regression and confidence intervals (a little long)

 From Petitti Tommasangelo To "'statalist@hsphsun2.harvard.edu'" Subject st: Logistic regression and confidence intervals (a little long) Date Thu, 29 Aug 2002 10:28:35 +0200

Title: Logistic regression and confidence intervals (a little long)

Dear STATAusers,
Suppose I perform a logistic regression on this dataset:

Variable        Data
-----------------------------------
sym             binomial
type            binomial
dumclass3       binomial

So the command is:

logistic sym type pH

Suppose I've this result:
------------------------------------------------------------------------------------
Logit estimates                                   Number of obs   =       4848
LR chi2(2)      =     297.12
Prob > chi2     =     0.0000
Log likelihood = -752.84441                       Pseudo R2       =     0.1648

------------------------------------------------------------------------------
sym | Odds Ratio   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
type |   10.98154   1.644385    16.00   0.000     8.188485    14.72729
dumclass3 |    1.63897   .2841108     2.85   0.004     1.166857    2.302101
------------------------------------------------------------------------------

------------------------------------------------------------------------------------
Now ... it's clear that when dumclass3=0 then OR being type=1 and sym=1 is 10.98,
and when dumclass3=1 then OR being type=1 and sym=1 is 10.98*1.63=17.89

The question is: which is the CI for the OR 17.89? Is it 8.1*1.1=9.4
and 14.7*2.3=33.8 (i.e. the product of the two CI)?

Thanks for the anwers you'll send me.

Dr. Tommasangelo PETITTI
---------------------------------------
Medical Directorate
University Hospital Campus Biomedico
+39-6-22541521