s-news
[Top] [All Lists]

Re: logistic regression - no R squared or F output in long format

To: Scott Clark <scott.clark@adelaide.edu.au>
Subject: Re: logistic regression - no R squared or F output in long format
From: Frank E Harrell Jr <f.harrell@vanderbilt.edu>
Date: Thu, 24 Feb 2005 08:53:29 -0500
Cc: s-news@lists.biostat.wustl.edu
In-reply-to: <000001c51a72$c27245f0$5cf07f81@Scott>
References: <000001c51a72$c27245f0$5cf07f81@Scott>
User-agent: Mozilla Thunderbird 0.9 (X11/20041105)
Scott Clark wrote:

Hi all,
Just wondering if anyone can help a beginner - having trouble getting an R squared output from logistic regression in splus 6.2 student version. I get Deviance Residuals, Min 1Q Median 3Q Max, Coefficients, Value Std. Error, t value, intercepts, null deviance, Residual deviance, degrees of freedom, missing values and fisher score iterations *BUT NO R squared or F test figures using the long format, no matter how I change the dialog box.* * * Thanks Scott Clark Adelaide University Health Informatics Unit
--
Internal Virus Database is out-of-date.
Checked by AVG Anti-Virus.
Version: 7.0.300 / Virus Database: 265.8.8 - Release Date: 14/2/2005


Scott,

First you need to be clear on what you want. Do you want ordinary R^2? It's easy to calculate yourself using the command line. Do you want the R^2 that has been generalized to handle models fitted by maximum likelihood and not just least squares? You can use the lrm function in the Design library that is pre-installed in S-Plus. Do you want another index such as ROC area that is more interpretable? Look at lrm.

--
Frank E Harrell Jr   Professor and Chair           School of Medicine
                     Department of Biostatistics   Vanderbilt University

<Prev in Thread] Current Thread [Next in Thread>