I’m curious why you don’t think the specific numbers can be trusted.
This post is the first step in an ongoing project to build a formal model for evaluating interventions. As a result, a lot of the numbers I give here are pretty rough. I’ve changed some of them since writing this and will probably change some more. I’m working on a customizable spreadsheet that will allow people to put in their own inputs and get a posterior. I want people to be able to use the process I describe in this essay, but I don’t go into much detail on how I performed calculations since I’m going to do that later.
In short, I believe the results in this post are mostly correct but you should consider it a rough first attempt.
This post is the first step in an ongoing project to build a formal model for evaluating interventions. As a result, a lot of the numbers I give here are pretty rough. I’ve changed some of them since writing this and will probably change some more. I’m working on a customizable spreadsheet that will allow people to put in their own inputs and get a posterior. I want people to be able to use the process I describe in this essay, but I don’t go into much detail on how I performed calculations since I’m going to do that later.
In short, I believe the results in this post are mostly correct but you should consider it a rough first attempt.