05-24-2015 12:51 PM
Pardon if this is an easy question, I'm pretty new to SAS and logistic regression in general.
Model: Response variable is dichotomous (1=ems heli transport, 0 = other form of trans). Model includes 6 explanatory variables - 3 continuous (age, injury severity, distance from hospital) and 3 categorical (race, arrival time in ED, and injury mechanism).
I have found significant interaction between race (categorical) and distance from hospital (continuous), but only for one of the categories (hispanic, all of the others are nonsignificant). I don't want to stratify because race is the explanatory variable that I am most interested in. How should I treat this? Can't seem to find answers anywhere, and most of the literature has the categorical variable as dichotomous. Thanks!
05-26-2015 07:23 AM
There really isn't anything to "treat". You just report the results for all the levels of race.
If there is an interaction between race and distance, then there is an interaction - it makes no sense to say the interaction exists only at one level of race. That would be the equivalent of saying "Me are taller than women, but women aren't shorter than men".
In addition, "significance" is a bad guideline for including or excluding a variable.
But beware if any of your levels of race have small n. That could cause problems and you could deal with those by either combining categories or deleting some people (E.g. if you use the standard US Census levels of race, then, in most of the USA, there will be very small numbers of "Native Hawaiian or Pacific Islander" and "American Indian or Alaskan Native". In some areas there will be small numbers of other categories as well (not a lot of African Americans in Maine, for example).
05-26-2015 08:10 AM
My suggestion is removing interaction effect between race (categorical) and distance from hospital .
then fit model again . Maybe 'distance ' took too much effect from 'race' .
Check these category variable's main effect is significant or not before include the next interaction effect .