In this post, we looked at how many (Covid-19) tests one (Jon) would have to take to obtain a certain accuracy; Jon would need to test 9 times to obtain (more than) 99 $\%$ accuracy with a Covid-19 test that is 85 $\%$ accurate using the LRT based decision rule. To answer this question we did a power analysis to obtain the minimum number of tests we would need for our likelihood ratio test to attain a certain power.

If Jon has 10000 covid-19 test kits with $85\%$ accuracy costing $£8$ a piece, assuming each test kit is drawn from an identical independent distribution (i.i.d.), how much does Jon need to spend to get $99\%$ accuracy?

Suppose you independently sample uniformly from the unit interval and then sum these samples. On average how many times would you have to do this before the sum is bigger than one?

Welcome to my Github page. Here I collect and link to beta and final versions of software and manuscript that I’ve produced. My work is focused on statistics, particularly computational statistics with a lean towards high dimensional and machine learning themes, so basically statistical learning.