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

From |
"Martin Weiss" <martin.weiss1@gmx.de> |

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

Subject |
st: Re: |

Date |
Sat, 7 Feb 2009 18:30:05 +0100 |

<>

HTH Martin _______________________

To: "Stata list" <statalist@hsphsun2.harvard.edu> Sent: Saturday, February 07, 2009 5:29 PM

Hello Statlist:I have an OLS model that looks like this: y = constant + b + c + d + e +f.c is the variable in which I am most interested. In the basic model, cturns out NOT to be significant (it is not even close).However, when I include an interaction term in the model, c*f, c turns outto be highly significant.So the new model looks like this: y = constant + b + c + d + e + f + c*f.The interaction term, c*f, is highly significant as well (though in manyversions f is NOT significant).My question is this: Is it defensible JUST to report the results of thefully specified model--that is, the one with the interaction? I kind offeel bad knowing that the first model does not produce the results Idesire (I am very happy c ends up significant in the full model--it helpssupport my hypothesis). I have heard from others that if the variable ofinterest is NOT significant without the interaction term in the model butIS significant WITH the interaction term, I should either a) report theresults of both models; or b) assume the data are screwy and back away...What do you all think? Thanks so much. Antonio Silva _________________________________________________________________ Windows LiveT: Keep your life in sync. http://windowslive.com/howitworks?ocid=TXT_TAGLM_WL_t1_allup_howitworks_022009 * * 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/

**References**:**[no subject]***From:*Antonio Silva <asilva100@live.com>

- Prev by Date:
**st: Re:** - Next by Date:
**st: prediction in loglinear regression model** - Previous by thread:
**st: Re:** - Next by thread:
**st: prediction in loglinear regression model** - Index(es):

© Copyright 1996–2016 StataCorp LP | Terms of use | Privacy | Contact us | What's new | Site index |