CarmenTamayo
commented
2 weeks ago Hello @ginacuomo! I've had a look at this use case- to clarify, which parameter would be erroneously reported in the literature in this case? is it ambiguous reporting of whether the CFR estimate was adjusted for delays or not? Also, when I run the code I'm encountering this problem, does it happen for you too? :
delay_density = function(x) dgamma(x, shape = 2.40, scale = 3.33) Total deaths = 131 and expected outcomes = 126 so setting expected outcomes = NA. If we were to assume total deaths = expected outcomes, it would produce an estimate of 1.
So the adjusted CFR is not included in the plot, I think it's because the number of expected outcomes in this case, with the distribution that's being used, results in a lower number than the number of deaths, I believe this is due to the chosen cutoff date (maybe because it's at a point in the outbreak with many recorded deaths) I've tried choosing another date that's in the growing phase, even 25/09, and the code works correctly Let me know your thoughts! Thanks
ginacuomo
Example of naive vs adjusted CFR when estimating this real-time. Rmd contains intro to problem, method, discussion plus a figure and a caption. Couldn't figure out how to merge this into the manuscript/if we even want to keep it but please let me know what you need me to do @joshwlambert