August 5, 2022
Briefly
- There’s a new version of ESR’s Wastewater Covid dashboard. It has information on which variants are being found, by location and over time
- Hashigo Zake, the Wellington craft beer bar, has a new Twitter bot tweeting out the CO2 concentration inside the bar. I summarised a couple of days of it:
- How far can you go by train in 5 hours? A map of Europe
- How likely are people to win the lottery: the Washington Post did a quiz
- Jamie Morton in the Herald has a good discussion of the Stats NZ review of the population denominator used in Covid vaccine stats. The HSU undercounts somewhat, especially for Māori and Pacific Peoples, but it has the virtue of counting ethnicity the same way that the vaccination data does, and of including people in NZ who are not residents.
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 »
As I understand it, the thing about the HSU dataset is that, while it may have had fewer people than it should have, it actually contained real people identified and known to the health service, rather than being administratively constructed, enhanced or embellished.
Also, the HSU dataset has matching numerator and denominators; in other words, the same people are in both. That means rates are what they look like, numerically anyway. Of course, there may be people who have not been in touch with the health system and these rates will not represent them, but the rates are accurate for the population on which they are calculated, which is better than having non-matching numerators and denominators.
But the downside is that these are people in touch with the health system. Accurate rates, but of a subset, albeit a major one (what proportion of people are not in touch with the health system at all – 10%?).
The other thing is to move to measures of ethnic identification the reduce the likelihood of a mismatch between numerator and denominator. So, if you have a census denominator but a health system numerator, different ethnic identities may be constructed/reported.
2 years ago
As well as the people being missed there is the issue of people being counted twice (or more). And that differs by ethnicity too.
2 years ago
For 10 years now they having been using software to match those who have multiple NHI numbers. So I dont think its a big issue where people are counted twice.
2 years ago