Add new comment

Comment: 

This is not a problem with our analysis because we include former smoking as well as e-cig use in our logistic regression model.  So the effects of any former smoking is captured directly rather than as an artifact in any of the e-cig variables.

In addition, for that to be inducing an artifact in our results smokers who had MIs would have had to try quitting with e-cigarettes at a much higher rate than smokers who did not have MIs trying to quit.  There is no reason to expect that to be the case.

Plain text

  • No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.