[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

# st: RE: Missing Value & Logistic regression

 From "Naji Nassar \(MIReS\)" To Subject st: RE: Missing Value & Logistic regression Date Mon, 24 Nov 2003 14:26:16 +0100

```Barber,

Two options to consider:
1- You can compare both models over observations with no missing values on
FUMATIPO.
Just modify your if command in the old model. Simple way but loss of 242
observations
2- You can add a variable (MISSING(FUMATIPO)) in interaction with your old
and new model
Old model = OldModel1 if (missing FUMATIPO)) OldModel2 (if not missing
FUMATIPO) whatever FUMATIPO value is
New model = NewModel1 if (missing FUMATIPO)) NewModel2 (if missing FUMATIPO
+ i.FIMATIPO)
More complexe, possible overparam. but you'll have all the observations

Best
Naji

-----Message d'origine-----
De : owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu]De la part de Xavi Barber
Envoye : lundi 24 novembre 2003 13:50
A : statalist@hsphsun2.harvard.edu
Objet : st: Missing Value & Logistic regression

Dears stata users:

I'm doing  a logistic regression, and now i have ajusted  by sex,
age and others variables.

My question is:
My old model: xi:logistic esofago i.sexo1 i.edad3c
i.estudi3c i.tipobeb2 i.fuma1  if fil_bebe==1
My new model: xi:logistic esofago i.sexo1 i.edad3c
i.estudi3c i.tipobeb2 i.fuma1  i.fumatipo if fil_bebe==1

but the problem is that FUMATIPO have 242 missing values.

I need to put the result in a typical journal table -->
Case - Control  ; Mean (stad. desv)  ; OR  IC(OR)

but, i can to compare the 1st model vs then 2nd model??

thanks

*
*   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/

*
*   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/
```

 © Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index