# Re: [R] logit model interpretation

From: Petr Klasterecky <klaster_at_karlin.mff.cuni.cz>
Date: Tue, 05 Jun 2007 22:40:36 +0200

Hi,

this is a standard (logistic) regerssion output and the meaning of coefficients and other terms is described in standard textbooks. Applied linear statistical models by Neter, Kutner, Nachtsheim & Wassermann is a good start to regression in general, (An introduction to) Categorical data analysis by Agresti are excellent monographs that cover logistic regression as well.

Petr

violeta834 napsal(a):
> Hello everyone
>
> I appologize for my lack of experience in statistical methods. I am an R
> user begginer and I am running a logit model using "zelig" and "pcse"
> packages. I will go to the point and is that Im having problems with
> interpreting the results of my models.. It is really simple (I guess for the
> most advanced scholars) however I really dont understand how to interpret
> the coefficients.
>
> here is my output
>
> Call:
> zelig(formula = newtrst ~ stfdem + stfgov + clsprty, model = "logit",
>
> Deviance Residuals:
> Min 1Q Median 3Q Max
> -2.784 0.318 0.410 0.540 1.460
>
> Coefficients:
> Estimate Std. Error z value Pr(>|z|)
> (Intercept) -0.6434 0.2427 -2.65 0.008 **
> stfdem 0.2447 0.0441 5.55 2.8e-08 ***
> stfgov 0.2050 0.0468 4.38 1.2e-05 ***
> clsprty 0.4173 0.1649 2.53 0.011 *
> ---
> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
>
> (Dispersion parameter for binomial family taken to be 1)
>
> Null deviance: 1112.46 on 1427 degrees of freedom
> Residual deviance: 996.02 on 1424 degrees of freedom
> AIC: 1004
>
> Number of Fisher Scoring iterations: 5
>
>
> Thanks
>
> Vioelta
>
>

```--
Petr Klasterecky
Dept. of Probability and Statistics
Charles University in Prague
Czech Republic

______________________________________________
R-help_at_stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help