Strange question, I know 🙂

]]>Quick question: What color theme are you using for your code?

Is that TextMate? Sublime Text?

Hello! I am a PhD student from Singapore in my first year. I had some problem in comprehending the OR to RR conversion. Your article did help me clear a few doubts 🙂

For my longitudinal cohort project, currently I am converting OR (obtained from binary logistic regression, SPSS) to RR using the formula:

RR = OR / (1 – p + (p x OR)) , as you have mentioned.

I would like to clarify a few doubts (apology if they are too amateur!):

Query-1: As per the definition, I am considering the reference group of each confounder as the non-exposed group, and thus, calculating the incidence of outcome in the non-exposed group for each confounder. Is this method accurate?

Query-2: If the above method is accurate, the dichotomous categorical variable is easy to calculate. But how do I calculate for the continuous variable e.g. age?

Thank you so much for your help!

Regards,

Tosha

Interesting blog! Thanks for the link!

However, I did not write that a fitted model is necessarily IP. Publication of the model and code necessarily places it in the public domain.

Regards,

Thomas

]]>