Notice: On March 31, it was **announced** that Statalist is moving from an email list to a **forum**. The old list will shut down on April 23, and its replacement, **statalist.org** is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

From |
Morten Hesse <mh@crf.au.dk> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
Re: st: compare effect size between dummys and metrics variables in logistic regression |

Date |
Mon, 27 Sep 2010 12:59:49 +0200 |

Hi

test [continuous covariate]=[1.dichomotomous covariate]

( 1) [dep var]cont_covar - [dep var]1.dic_covar = 0 chi2( 1) = 4.28 Prob > chi2 = 0.0387

Greetings Morten Den 27-09-2010 09:21, Michael N. Mitchell skrev:

Greetings JoergIf you were doing an OLS regression, I would say that you couldreport the partial (or semi-partial) correlation associated with eachof the variables. However, as you note, you are using binary logisticregression. While you could technically create z scores for the binaryvariables to try and put them on the same scale as the z-transformedvariables, those results would not make much sense. You could take thez-transformed variables and convert them into 0/1 variables by cuttingthem into two arbitrary groups, but that would not make much sense. Mythoughts are that there is not much you can do to compare the "apples"and "oranges" here in terms of the effect size.Best regards, Michael N. MitchellData Management Using Stata -http://www.stata.com/bookstore/dmus.htmlA Visual Guide to Stata Graphics -http://www.stata.com/bookstore/vgsg.htmlStata tidbit of the week - http://www.MichaelNormanMitchell.com On 2010-09-26 11.23 AM, Jörg Eulenberger wrote:Dear Statalisters,a have an more statistical Question. I want to calculate an binarylogistic regression. Ihave all metric variables z-transformed (mean = 0, std=1) to comparethe effect sizebetween the independent variable. But I have also dummys in myRegressionmodell. What cani do to compare the effect size of the dummy's with the effect sizeof the metricindependent variables? Or is that completely impossible? Thanks, Joerg * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/* * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

* * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

**Follow-Ups**:**Re: st: compare effect size between dummys and metrics variables in logistic regression***From:*Maarten buis <maartenbuis@yahoo.co.uk>

**References**:**st: Book on Propensity Scores***From:*"Michael N. Mitchell" <Michael.Norman.Mitchell@gmail.com>

**Re: st: Book on Propensity Scores***From:*Santosh Kumar <santosh.uh@gmail.com>

**st: compare effect size between dummys and metrics variables in logistic regression***From:*Jörg Eulenberger <j.eulenberger@web.de>

**Re: st: compare effect size between dummys and metrics variables in logistic regression***From:*"Michael N. Mitchell" <Michael.Norman.Mitchell@gmail.com>

- Prev by Date:
**Re: st: foreach and levels of string variable** - Next by Date:
**Re: st: tabout for multiple likert-scale questions** - Previous by thread:
**Re: st: compare effect size between dummys and metrics variables in logistic regression** - Next by thread:
**Re: st: compare effect size between dummys and metrics variables in logistic regression** - Index(es):