[S] Re: Interpreting Logistic regression - CORRECTION to Wald Statistic

Renaud Lancelot (lancelot@telecomplus.sn)
Fri, 30 Oct 1998 18:29:50 +0000

I was on the field this week and could not read S-news. Many thanks to
Siftikhar Sikder for noticing my error about the t-value in logistic
regression results. I apologize if this caused any trouble to anybody. I
do agree that one must square the t-value before performing the Wald
test, and that Wald test sometimes gives strange results. However, it
might be a useful statistics in many cases. In my practical experience,
disagreement between Wald test and likelihood ratio test is an
indication whether results are unstable.

Best regards,


andrew_white@hmsa.com wrote:
> Please note one error in the comments that Renaud Lancelot provided in
> [snews subject "Re: [S] Logistic regression problems in Standard Version",
> from: siftikhar sikder, date: october 18, 1998].
> In interpreting the significance of the individual coefficients using the
> t-values supplied in the summary(glm.object.fit) function, you must treat
> the SQUARE of these t-values as asymptotically Chi-Squared with 1 df, hence
> can test against, e.g., the critical value of 3.84 for 5% confidence level.
> Do NOT apply the t-value straight as the Chi-Squared value. The t-value
> reflects a Wald statistic indirectly, and there is S-News prior messages on
> the meaning of Wald statistics, as well as how to be VERY CAUTIOUS about
> Wald statistics in logistic regression (due to the obscure "Hauck-Donner
> effect") when the Beta coefficients are very large. But the t-value straight
> off is an approximation to a z-score, and better treated by SQUARING it to
> approximate a Chi-Square value.

Renaud Lancelot
BP 2057 Dakar-Hann

tel (221) 832 49 02 fax (221) 821 18 79 email renaud.lancelot@cirad.fr ----------------------------------------------------------------------- This message was distributed by s-news@wubios.wustl.edu. To unsubscribe send e-mail to s-news-request@wubios.wustl.edu with the BODY of the message: unsubscribe s-news