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

From |
"Michael I. Lichter" <mlichter@buffalo.edu> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
Re: st: Basic regression interaction term question |

Date |
Fri, 10 Oct 2008 15:03:23 -0400 |

Thanks Nick & John! I'll check out those references. Michael Nick Cox wrote:

First flag: This is a controversial area. Experts disagree.There is a brief but penetrating discussion of this issue within McCullagh, P. and Nelder, J.A. 1989. Generalised linear models. Chapmanand Hall.Search also for Nelder's writings on what is called the heredityprinciple.Nickn.j.cox@durham.ac.ukJohn Antonakis Yes. What's important is the coefficient of the AB term. The test A B ABis simply the F-test that the coefficients are simultaneously differentfrom zero. If you care about interaction, AB is what is important,regardless of the significance of B or A or A B or A B AB..Here is an interesting paper about this question: Bedeian, A. G., andMossholder, K. W. Simple Question, Not so Simple Answer: InterpretingInteraction Terms in Moderated Multiple Regression. Journal ofManagement, 1994, 20, 159-165 (get it here:http://www.bus.lsu.edu/management/faculty/abedeian/articles/SimpleQues-JOM1994.pdf).Michael I. Lichter wrote:Suppose you regress Y on A and B, and you expect an interactionbetween A and B.In the regression Y = A + B, the coefficient for B is not significant,but you have reason to think that it will be significant once youintroduce the interaction term.However, in the regression Y = A + B + AB, the coefficient for Bremains non-significant even though the coefficient for AB issignificant. Yet, "test A B AB" is significant.Is it reasonable to treat this as a significant interaction?What if AB is not significant either but "test A B AB" is stillsignificant?* * 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/

-- Michael I. Lichter, Ph.D. Research Assistant Professor & NRSA Fellow UB Department of Family Medicine / Primary Care Research Institute UB Clinical Center, 462 Grider Street, Buffalo, NY 14215 Office: CC 125 / Phone: 716-898-4751 / E-Mail: mlichter@buffalo.edu * * 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: Basic regression interaction term question***From:*"Michael I. Lichter" <mlichter@buffalo.edu>

**Re: st: Basic regression interaction term question***From:*John Antonakis <John.Antonakis@unil.ch>

**RE: st: Basic regression interaction term question***From:*"Nick Cox" <n.j.cox@durham.ac.uk>

- Prev by Date:
**Re: st: loop to rename vars** - Next by Date:
**Re: st: forvalues and _N** - Previous by thread:
**RE: st: Basic regression interaction term question** - Next by thread:
**Re: st: Basic regression interaction term question** - Index(es):

© Copyright 1996–2015 StataCorp LP | Terms of use | Privacy | Contact us | What's new | Site index |