I entirely agree with the main thrust of the Portland Press Herald’s editorial concerning America’s shameful neglect of Puerto Rico (“Our View: Puerto Rico’s problems are years in the making,” June 8).

However, there’s a fairly serious misunderstanding in that editorial, one that originates with the fact-checking organization PolitiFact.

It’s not true that the Harvard estimate of about 4,600 dead in Puerto Rico is merely the midpoint between the upper and lower confidence intervals (8,500 and 800 deaths, respectively), and so no more likely to be true than any other number in that range.

The Harvard study assumes a normal distribution – a “bell curve” – for the occurrence of deaths through time. There may be different factors that can skew a normal distribution, but it does not indicate that any one value in that distribution is as likely as any of the others – and, generally, it may indicate that a value in the center of the distribution is more likely than estimates at the extremes.

Bottom line: We don’t know the exact number of deaths in Puerto Rico caused by Hurricane Maria, but somewhere in the 4,000s is probably not a bad estimate.

Only subscribers are eligible to post comments. Please subscribe or login first for digital access. Here’s why.

Use the form below to reset your password. When you've submitted your account email, we will send an email with a reset code.