Variance only increases chance of Yes here. If cases spike and we’re averaging over 100k, reporting errors won’t matter. If we’ve averaging 75k, a state dumping extra cases could plausibly push it over 100k
To rephrase that, “Yes” requires that at least one day has reported >100k cases while “No” requires that all days have reported <100k cases. So if there is variance it will increase the chance any given day will be reported wrongly and a single wrong reporting of >100k will make “Yes” inaccurately occur. Of course, if it only spikes >100k real cases on a few days, and those days also have variance, that will make “No” inaccurately occur, but I agree that that’s an unlikely situation.
The real problem would be if the CDC has a consistent reporting error. For example if some states with high real case counts were to stop reporting data and the CDC then extrapolated from the remaining lower case count states, they could report an inaccurately low number of cases.
Variance only increases chance of Yes here. If cases spike and we’re averaging over 100k, reporting errors won’t matter. If we’ve averaging 75k, a state dumping extra cases could plausibly push it over 100k
To rephrase that, “Yes” requires that at least one day has reported >100k cases while “No” requires that all days have reported <100k cases. So if there is variance it will increase the chance any given day will be reported wrongly and a single wrong reporting of >100k will make “Yes” inaccurately occur. Of course, if it only spikes >100k real cases on a few days, and those days also have variance, that will make “No” inaccurately occur, but I agree that that’s an unlikely situation.
The real problem would be if the CDC has a consistent reporting error. For example if some states with high real case counts were to stop reporting data and the CDC then extrapolated from the remaining lower case count states, they could report an inaccurately low number of cases.