0

I'm trying to model market share (dependent variable) which is between 0 and 1. My boss told me to use Logistic Regression, but when I use the stepwise logistic regression with the backwards direction, my final model is only the intercept. Is this cause logistic regression should only be used when the dependent variable stricly 0 or 1? Is there anyway to model this scenario in R with the logistic regression while also using a step direction?

Thanks

JVMaverick
  • 49
  • 6
  • You don't seem to have much knowledge about statistics, and you want to model market share? Good luck. Also, if the step function only returns an intercept it's telling you that it cannot find any significant variables that predict market share, hence why it only selects an intercept, . – user2974951 Oct 05 '18 at 10:31
  • Yeah, I only have the basic understanding of statistics. But cheers thanks, that's what I thought. – JVMaverick Oct 05 '18 at 13:40

0 Answers0