0
$\begingroup$

Possible Duplicate:
What if interaction wipes out my direct effects in regression?

We have a question regarding a regression we are working on. We have two dummy variables, net income (If net income this year is higher than last year it equals 1, and 0 if opposite) and cash bonus (1 if cash bonus, 0 if no cash bonus). The dependent variable is derivatives use (1= use of derivatives, 0= no use of derivatives). We also have several other independent variables (both categorical and continuous), but we have made an interaction term by using the two dummy variables. When including all three components (the interaction term and dummy variables), none turns out significant. However, when we only include the interaction term it is significant, and also when including all other independent variables (exept from the two dummies that the interaction term is constructed from). Would it be okay to only include the interaction term in the model? Also, there is a high degree of collinearity between the two dummies and the interaction term. We are interested in finding out what factors may cause firms to use derivatives. We see from other similar questions that some argue that it is okay and other who argue that it is not okay. We would really apprectiate someones help on this or if someone could refer us to litterature where it describes when it is okay to only include the interaction term.

Improve this question
$\endgroup$
  • 1
    $\begingroup$ For more information (in addition to the duplicate thread), please review the four dozen (or so) related questions. $\endgroup$ – whuber♦ Jul 10 '12 at 12:34
0
$\begingroup$

There are other discussions on this site where the inclusion of interaction terms in regression without main effect is discussed. The issue is the same in logistic regression. Nothing prevents this from being possible. It is just a common rule without thorough justification that itneractions should not be included without main effects.

Improve this answer
$\endgroup$
  • $\begingroup$ Thank you for your response. However, do you have any suggestions as to where we might find litterature supporting that one does not need to include the main effects? Since the common rule is stated several places, we should have a justification for not including them in our assignment. Thank you again though! $\endgroup$ – Eleonora Jul 10 '12 at 12:53
  • 1
    $\begingroup$ Michael, as evidenced by your answer, you were clearly aware that this was a duplicate question. In such situations you (and everyone with 3000+ rep) are encouraged to use your close votes! This is a simple and valuable service to the CV community that is sorely needed since most of the 50 or so 3000+ rep users never do this, making the question closing mechanism essentially useless on this site and leaving it to the moderators to make unilateral decisions. Since moderators are not omniscient, this leads to things "falling through the cracks", with lots of should-be-closed questions remaining. $\endgroup$ – Macro Jul 10 '12 at 12:53
  • $\begingroup$ With you being on the site so frequently, you could provide valuable help on this front $\endgroup$ – Macro Jul 10 '12 at 12:54
  • 1
    $\begingroup$ @Eleonora, please peruse these threads: stats.stackexchange.com/… and, if you still cannot find your answer there, perhaps you can edit your question about what specifically you can't find and it can be reopened, if appropriate. $\endgroup$ – Macro Jul 10 '12 at 12:55
  • $\begingroup$ @Eleonora, specifically, I think these threads: stats.stackexchange.com/questions/27724/… and stats.stackexchange.com/questions/11009/… will be helpful for you. $\endgroup$ – Macro Jul 10 '12 at 13:04

Not the answer you're looking for? Browse other questions tagged or ask your own question.