# st: use of logistic

 From Ann Fitzmaurice <[email protected]> To [email protected] Subject st: use of logistic Date Mon, 14 Jun 2004 12:34:10 +0100

hi

i have data thast was collected at the individual level, but the pupils are from different schools

i have tried the following with and without the cluster option

what i am trying to do is to see if there are any school effects but not sure if logistic is the right method, and if so , how can i tell from the output if there are are school effects

. xi:logistic E35_LR1 i.REGION, cluster( SCHOOL)
i.REGION _IREGION_1-2 (naturally coded; _IREGION_1 omitted)

Logit estimates Number of obs = 8539
Wald chi2(1) = 4.52
Prob > chi2 = 0.0334
Log likelihood = -4459.2514 Pseudo R2 = 0.0039

(standard errors adjusted for clustering on SCHOOL)
------------------------------------------------------------------------------
| Robust
E35_LR1 | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
_IREGION_2 | 1.39198 .216436 2.13 0.033 1.026317 1.887924
------------------------------------------------------------------------------

. xi:logistic E35_LR1 i.REGION,
i.REGION _IREGION_1-2 (naturally coded; _IREGION_1 omitted)

Logit estimates Number of obs = 8539
LR chi2(1) = 35.32
Prob > chi2 = 0.0000
Log likelihood = -4459.2514 Pseudo R2 = 0.0039

------------------------------------------------------------------------------
E35_LR1 | Odds Ratio Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
_IREGION_2 | 1.39198 .0784069 5.87 0.000 1.246484 1.554459
------------------------------------------------------------------------------
regards
ann

------------
Ann Fitzmaurice
Medical Statistician
Dugald Baird Centre for Research on Women's Health
Aberdeen Maternity Hospital
University of Aberdeen
Aberdeen AB25 2ZL
Uk
[email protected]

Tel . 01224 553876

*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/