A headline in the Washington Post (April 26, 2020), based on the researchers’ conclusions at the time, blared, “In New York’s largest hospital system, 88% of coronavirus patients on ventilators didn’t make it.” (As of April 25, the headline wasn’t corrected. By May 5, it had been changed to read “…many patients on ventilators didn’t make it.”)
The ventilator mortality rate excluded from the denominator patients still in the hospital.
After an immediate outcry from others in the medical community, the research paper was corrected in JAMA online:
“The sentence reporting mortality for patients receiving mechanical ventilation should read, ‘As of April 4, 2020, for patients requiring mechanical ventilation (n = 1151, 20.2%), 38 (3.3%) were discharged alive, 282 (24.5%) died, and 831 (72.2%) remained in hospital.'”
This is one example — the cornovirus pandemic has provided many — of the importance of proper denominators.
Denominators often are not scrutinized closely enough by journalists, by businesses, or by wellness professionals. The gross oversight described here reminds us that, without any background in statistics or data science, denominators used in calculations — when, indeed, they are used — are one reasonable starting point (population size is another) when interpreting data.