Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Model goodness-of-fit

From   SR Millis <>
Subject   Re: st: Model goodness-of-fit
Date   Wed, 15 Sep 2004 05:33:45 -0700 (PDT)

Have you performed routine diagnostics, eg, examined
residuals, checked for outliers and overly influential
observations, ruled out multicollinearity, checked for
linearity in the logit, etc?

SR Millis

--- Subhash Pokhrel
<> wrote:

> Dear List members,
> I have two continuous variables and eight dummy
> variables in a logistic
> regression model (n= about 17,500). I tried to test
> the model goodness of
> fit with Hosmer Lemeshow test which gave me large
> chi2 value with very small
> p value, showing the lack of fit. If I drop one of
> the two continuous
> variables from the model, I get much smaller Chi2
> with large p values. Since
> this is the most important variable I would like
> have in the model, I would
> appreciate receiving your suggestion as to how I
> could solve this problem.
> Is there any other tests available in Stata?
> Surprisingly, while searching
> the net I came across a very big criticism of using
> Hosmer-Lemeshow test.
> Thanks,
> Subhash.
> *
> *   For searches and help try:
> *  
> *
> *

Scott R Millis, PhD, MEd, ABPP (CN & RP)
Director, Office of Clinical Trials
Kessler Medical Rehabilitation Research & Education Corp
1199 Pleasant Valley Way
West Orange, NJ  07052

This electronic message may contain information that is confidential
and/or legally privileged. It is intended only for the use of the
individual(s) and entity named as recipients in the message. If you are
not an intended recipient of this message, please notify the sender
immediately and delete the material from any computer. Do not deliver,
distribute or copy this message, and do not disclose its contents or
take any action in reliance on the information it contains. Thank you.
*   For searches and help try:

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