A new study in @PNASNews claims to provide evidence that covid vaccine mandates reduced covid booster and flu vaccine uptake. They provide the replication code for the DiD models, but... these are not DiD models and that is not an interaction term. https://www.pnas.org/doi/10.10...
Someone with more time an interest than me should give this a properly thorough review, but this seems pretty bad.
@jfeldman_epi @PNASNews I agree this looks very weird but R actually *does* create the proper interaction with (baseline_att + before_after)^2 (much to my initial surprise)
@jfeldman_epi @PNASNews yikes!
@jfeldman_epi @PNASNews It is an interaction term, but it isn't the right one for a standard diff-in-diff, no?
@jfeldman_epi @PNASNews They join @NateSilver538 in being too good for cluster robust standard errors.
@jfeldman_epi @PNASNews Looks weird!
@jfeldman_epi @PNASNews Maybe it’s just that I haven’t had my coffee/meds yet, but I’m having such a hard time parsing even the title of this article (let alone the actual text of it). An abundance of issues!