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 |
Thomas Speidel <thomas@tmbx.com> |

To |
<statalist@hsphsun2.harvard.edu> |

Subject |
Re: st: Evaluating the importance of interaction effects in logistic regression |

Date |
Wed, 31 Aug 2011 13:57:20 -0600 |

Thank you Maarten for the informative reply. On Wed, 31 Aug 2011 09:48:10 +0200, Maarten Buis wrote:

You cannot determine the significance without deciding how you wanttointerpret the results. Interpretation and significance are not independent, as the first determines the null hypothesis of the second. This is the key bit of information you need in order to see that I (Maarten) and Norton et al. do not disagree, even though these quotes make it seem like we do. I showed in my Stata tip how to interpret interaction terms as ratios of odds ratios, in which case you can interpret the p-values as the test that this ratio equals 1, i.e. there is no difference between black and white females in the effect (measured as odds ratios) of collgrad. Norton et al. want to interpret effects as marginal effects, i.e. as differences in probabilities rather than ratios of odds, and the marginal effect as differences (rather than ratios) in marginal effects. As aconsequence I and Norton et al. want to test different hypotheses,andobviously get different results.For example:

********************************************************************************

sysuse nlsw88, clear gen byte high_occ = occupation < 3 ifoccupation< &g> race==3 logistic high_occ race##collgrad , nolog is it correct to saythat the interacollgrad is not important because its p-value is 0.161? Such a conclusion is always wrong as a significance test cannot determine whether or not a variable is "important". This may soundpedantic, but this misunderstanding is probably the root cause ofyourconfusion. As soon as you regard tests as testing a specific null-hypothesis the distinction between me and Norton et al. becomesmuch easier to understand. As I stated above this tests thehypothesisthat the ratio of the effect (measured in odds ratios) of collgradforwhite women and the effect of collgrad for black women equals 1, i.e. that these effects are equal. If that is a hypothesis that is ofinterest to you, than this test is fine. If this> is not of interesttoyou, than this test is not fine. What if, forexample, we had 3 levels to race:

********************************************************************************

sorace race = 3 in 1/300 loocc race##collgrad, nolog and we want to evaluate the overall importance of the interaction between race and collgrad (i.e.jointly)?Is it approriate to use the likelihood ratio test to compare themodelwithout interaction to the model with interaction, and determine the importance of the interactiording based on the results of LR test?That depends on whether you want to interpret your results in termsofodds ratios and your interaction terms as ratios of odds ratios. If you want to do that, than what you propose is one way of doing that. Hope this helps, Maarten -------------------------- Maarten L. Buis Institut fuer Soziologie Universitaet Tuebingen Wilhelmstrasse 36 72074 Tuebingen Germany http://www.maartenbuis.nl [1] -------------------------- * * For searches and help try: * http://www.stata.com/help.cgi?search [2] * http://www.stata.com/support/statalist/faq [3] * http://www.ats.ucla.edu/stat/stata/ [4]

-- Thomas Speidel Links: ------ [1] http://www.maartenbuis.nl [2] http://www.stata.com/help.cgi?search [3] http://www.stata.com/support/statalist/faq [4] 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/

**References**:**st: Evaluating the importance of interaction effects in logistic regression***From:*Thomas Speidel <thomas@tmbx.com>

**Re: st: Evaluating the importance of interaction effects in logistic regression***From:*Maarten Buis <maartenlbuis@gmail.com>

- Prev by Date:
**Re: st: Question about pstest (after running psmatch2)** - Next by Date:
**Re: st: RES: generating a variable with pre-specified correlations with other two (given) variables** - Previous by thread:
**Re: st: Evaluating the importance of interaction effects in logistic regression** - Next by thread:
**st: atrho0() in mvprobit** - Index(es):