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 |
Verena Dill <dill@uni-trier.de> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
Re: st: Testing interaction terms / mutually exclusive variables |

Date |
Thu, 20 Jun 2013 19:01:41 +0200 |

Thanks a lot for your ongoing help! Am 20.06.2013 18:18, schrieb David Hoaglin:

Verena, If I may ask an ignorant question, in what way does -test- not take into account the fact that the two dummy variables are mutually exclusive? (I do not have Stata documentation handy.) If the two dummy variables are in the same regression model, the covariance matrix of the estimated coefficients reflects that structure. Can you use -lincom- after the regression command? I do not yet understand, however, why you would need -lincom-. The usual output from a regression includes a confidence interval for each coefficient, and the test of whether the coefficient is zero is equivalent to asking whether zero is in the confidence interval. If those two dummy variables are also exhaustive, one of them may be considered part of the definition of the intercept. Then the coefficient of the other dummy variable will be the estimated difference between the two categories (i.e., the additional intercept for the second category). David Hoaglin On Thu, Jun 20, 2013 at 11:53 AM, Verena Dill<dill@uni-trier.de> wrote:thank you so much again for your answer. After reading your reply and re-reading my emails I concluded that it may not have been the best way to explain my problem. I will try a better strategy: I have two dummy variables that are mutually exclusive. For example, a firm belongs to the service sector, to the manufacturing sector or other sectors. I am running a regression and want to test whether or not the estimated coefficients are signficantly different from zero. One approach is to use the post-estimation command "test". Howover, "test" does not take into account that the two dummy variables are mutually exclusive. Is there another procedure that does this? Thank you very much in advance Verena* * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/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/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/

**Follow-Ups**:**Re: st: Testing interaction terms / mutually exclusive variables***From:*David Hoaglin <dchoaglin@gmail.com>

**Re: st: Testing interaction terms / mutually exclusive variables***From:*Phil Schumm <pschumm@uchicago.edu>

**References**:**st: Testing interaction terms***From:*Verena Dill <dill@uni-trier.de>

**Re: st: Testing interaction terms***From:*David Hoaglin <dchoaglin@gmail.com>

**Re: st: Testing interaction terms***From:*Verena Dill <dill@uni-trier.de>

**Re: st: Testing interaction terms***From:*David Hoaglin <dchoaglin@gmail.com>

**Re: st: Testing interaction terms / mutually exclusive variables***From:*Verena Dill <dill@uni-trier.de>

**Re: st: Testing interaction terms / mutually exclusive variables***From:*David Hoaglin <dchoaglin@gmail.com>

- Prev by Date:
**Re: st: Followup to: simple slopes between continuous variable and dichotomous moderator** - Next by Date:
**Re: st: Testing interaction terms / mutually exclusive variables** - Previous by thread:
**Re: st: Testing interaction terms / mutually exclusive variables** - Next by thread:
**Re: st: Testing interaction terms / mutually exclusive variables** - Index(es):