I am grateful to moderator @jonc101x and speaker @jsross119 for allowing me to make a brief statement at the very interesting Stanford BMIR seminar yesterday (43:00 mark). A lightly edited text version follows: stanford.zoom.us/rec/share/ptFL…
I asked Jonathan and Joe if I could speak briefly to address inaccurate remarks made about me last week and try to say something constructive about how the scientific error-correcting process can work better.
May 1, 2020 • 24 tweets • 6 min read
The statistical analysis in the Bendavid et al. revision still seems to have at least one fatal bug.
medrxiv.org/content/10.110…
Tl;dr: The new data show that the specificity of the test kit varies across different samples. After accounting for this, the data are still too noisy to rule out zero or near-zero prevalence in Santa Clara County.
Apr 24, 2020 • 21 tweets • 7 min read
For the sake of transparency, I should elaborate on this point which I left vague before.
The authors said they used “ci means” in Stata on the 0/1 variables (test - / test +) for the 3330 participants, and they don’t know how the weights were used. I think I know, thanks to help from @achouldechova, @DonskerClass, @j_kalla, @StatStas, and Jas Sekhon.
Apr 21, 2020 • 17 tweets • 5 min read
I have been corresponding with the authors of the well-known Santa Clara County COVID-19 preprint, and I am alarmed at their sloppy behavior. The confidence interval calculation in their preprint made demonstrable math errors - *not* just questionable methodological choices.
Everyone makes mistakes, but the record must be corrected ASAP. I emailed them on Saturday morning asking them to do so. In the last three days they haven't corrected anything yet, but a subset of them have released a new study without saying how they did the analysis this time.
