Epidemiologists ought to think about GLM & IMR for higher Covid demise predictions and overcome testing bias

[This article was first published on R-posts.com, and kindly contributed to R-bloggers]. (You possibly can report problem concerning the content material on this web page right here)


Wish to share your content material on R-bloggers? click on right here if in case you have a weblog, or right here in the event you do not.

Social science analysis community (SSRN) reviewer has posted our “A Novel Resolution to Biased Knowledge in Covid-19 Incidence Research” written on my own (H D Vinod) and Okay Theiss.  It makes use of a brand new two-equation generalized linear mannequin (glm) with Poisson hyperlink for forecasting Covid-19 deaths within the US and particular person states. The primary equation explicitly fashions the chance of being examined. It helps construct an estimate of the bias utilizing inverse mills ratio (IMR) Detailed paper is obtainable free of charge obtain at:

ssrn.com/summary=3637682

It makes use of open-source R software program.  A complement to the paper entitled “State-by-state Forecasts of Covid-19 Deaths” is obtainable free of charge obtain at http://www.fordham.edu/economics/vinod/WeeklyCovid.pdf

Our bias-corrected out-of-sample demise forecasts for future weeks ought to assist state governors and mayors resolve on limits to opening native economies.  One can examine the efficiency of democratic versus republican governors utilizing the data tabulated.

Leave a Reply

Your email address will not be published. Required fields are marked *