July 15, 2021
Briefly
- From Radio NZ: an exegesis of the non-quantitative weakly graph-like thing that accompanied information about NZ vaccine rollout plans in March. This was unusually bad for a graph from the NZ public service, but I think the story is overthinking it.
- The FDA approval of aducanumab for Alzheimer’s disease seems may have been procedurally a bit dodgy as well as scientifically dubious. (STAT($), Washington Post)
- photochrome.io will take a word or phrase and give you a colour palette based on photos found using the word/phrase
- “Why are gamers so much better at catching fraud than scientists?” (I don’t think they are; they just care about it more)
- The US is having problems getting new electorates laid out because of the Census delays. In NZ, one of the constraints on the Census 2018 data quality improvement process was that it absolutely positively had to be done in time for the Representation Commission to make electorates.
- A twitter thread on finding evidence of secret US flights into Australia. Only not.
- Why housing costs aren’t in the Consumer Price Index (but are in other indexes, which you might want to use instead)
Thomas Lumley (@tslumley) is Professor of Biostatistics at the University of Auckland. His research interests include semiparametric models, survey sampling, statistical computing, foundations of statistics, and whatever methodological problems his medical collaborators come up with. He also blogs at Biased and Inefficient See all posts by Thomas Lumley »
Another issue with putting interest payments in CPI is that the house is an asset. At least that’s what people who buy houses claim. So if we put in rises in interest costs should we deflate it by house value (asset) rise?
3 years ago
At first I thought it was wrong but now I think it’s just badly labelled. The top line should be “people who have got the 2nd vaccination at this particular time point” (labelled second dose). The bottom line should be “people who have only had the first dose and not the second dose at this particular time point” (labelled first dose). So, as soon as people have the second dose they are no longer in the “first dose” group.
The cummulative is not “cumulative of people over time who have had each dose” but “cummulative of doses at each time point” (and excluding 0 – probably because 1) it won’t fit nicely on the graph and 2) it predicts how many people the MoH things are vaccine hesitant).
It’s a graph for process monitoring of the vaccine rollout not a good graph for explaining to people how the vaccine rollout is going.
3 years ago
I don’t think I explained it that well so here is an example…
If there are 10 people with 0 doses, and 4 people with 1 dose and 12 people with 2 doses.
And at this time point, 2 people get their first dose and 3 people get their second dose then
“0 dose” is 10 – 2 = 8 (how many still need a first dose today)
“1 dose” is 4 + 2 – 3 = 3 (how many still need a second dose today) and
“2 dose” is 3 (how many had a second dose today)
3 years ago