This post is in response to the increased use of lateral flow tests for Covid screening. I’ve had a number people asking about these. This includes people providing diagnostic tests who are being asked to provide lateral flow tests and …
Communicating risk with Covid testing the Bayesian way Read more »
I’ve been asked to write this because this question is one of the most commonly asked on Google, so lots of us have questions about our risk. We’re entering a phase of disease management where it is difficult to balance …
I’m a bit wary of becoming one of those armchair epidemiologists who’s wise after the fact and pontificates on what people under far more pressure decided when they didn’t have the benefit of hindsight. So I won’t. Pontificate, that is. …
I’ve written a couple of posts now on Covid-19 where I’ve mentioned that Germany is held up as a great example of success but where all-cause mortality data aren’t available. Well, now they are. On 22nd May, the Federal Statistical …
Back in April, I wrote a post about coronavirus because I was getting annoyed by the poor quality of statistical reporting and was trying to make sense of the situation myself. Today, I want to revisit the data I used …
I have’t posted on Monkeyglandin for a long time, but I want to share a little bit on the off chance that it’s of some use. A big part of good quality analysis is looking at the world objectively and …
This post arose because of a discussion with some colleagues about the measurement of utility and health-related quality of life in cancer. It covers latent variable regression and an attempt to use it to describe the relationship between a common …
Meta-analysis relies on the pooling of data from across studies. This can be a pain because study reports are not usually written with the intention of having their results pooled with other studies. Reports of meta-analyses are sometimes even worse …
Last month, the news was flooded (well, mildly soaked at least) with claims that the NHS is paying too much for drugs. My favourite headline was from the Telegraph, which claimed that researchers thought the ‘NHS should stop buying drugs …
Drug prices, lost opportunities, and the real cost of healthcare Read more »
This is just a quick note on using OpenBUGS in R. This is particularly handy if you need to run a series of models on a data set, or if you need to manipulate the output of Bayesian analyses in …
