id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-225183-6rusimb5	Boukai, Ben	Bayesian Modeling of COVID-19 Positivity Rate -- the Indiana experience	2020-07-09		.txt	text/plain	3108	235	68	In this short technical report we model, within the Bayesian framework, the rate of positive tests reported by the the State of Indiana, accounting also for the substantial variability (and overdispeartion) in the daily count of the tests performed. In this report we model, within the Bayesian framework, the rate of positive tests reported by the the State of Indiana, accounting also for the substantial variability of the daily number test performed. Remark: The choice in (2) for using the Negative Binomial distribution to model the reported daily number of tests k i , could be seen as specific to the Indiana COVID-19 testing data, which might reflect testing capacity limitation and daily variability unique to that state. In a similar manner we obtain the posterior predictive distribution under this Bayesian model and given (X m , N m ), of a 'new' (or 'future') number of tests K * is the Beta-Negative Binomial distribution.	./cache/cord-225183-6rusimb5.txt	./txt/cord-225183-6rusimb5.txt