I am trying to read this article that may explain the dangers associated with categorization and interpretability of Odds Ratio
https://www.tandfonline.com/doi/pdf/10.1080/03610928308831078?needAccess=true
I dont have access to the full text of that article. So I am wondering if someone can help me understand what are the problems that can arise if I dichotomize my outcome variable and estimate the ORs. Please note I am not randomly choosing a cut point. The cut points were chose based on literature review.
Thanks.