Mr. Steven Kopits takes issue with the Harvard School of Public Health led study’s point estimate of (4645) and confidence interval (798, 8498) for Puerto Rico excess fatalities post-Maria thusly:

Does Harvard stand behind the study, or not?

94 Replies

Mr. Steven Kopits takes issue with the Harvard School of Public Health led study’s point estimate of (4645) and confidence interval (798, 8498) for Puerto Rico excess fatalities post-Maria thusly:

Does Harvard stand behind the study, or not?

Since the Puerto Rican government ceased publishing mortality data in February, there has been a debate over the death toll arising from Hurrican Maria. The official death toll, focusing on direct deaths, remains at 64. However, starting in November, a number of scholars attempted to gain further insight into the extent of the human disaster in the Commonwealth. One commentator has labeled another study “garbage”. What is the import of these competing analyses?

In all the excitement between the Italian crisis and the US lashing out with tariffs to be levied against our allies, it was easy to overlook this event:

**Figure 1:** Ten year constant maturity Treasury minus three month Treasury bill yield spread on secondary market (blue), and ten year minus two year yield spread (green), both daily, %. Last observation is 6/1. Source: Federal Reserve via FRED, Bloomberg, and author’s calculations.

Continue reading

- Population mean
- Sample mean
- Population standard deviation
- Sample standard deviation
- Standard error
- Administrative data
- Survey data
- Point estimate
- Confidence interval
- Sampling bias
- Reporting bias

Now, let’s begin. Here is a graph of estimates of cumulative fatalities in Puerto Rico over time.

**Figure 1:** Estimates from Santos-Lozada and Jeffrey Howard (Nov. 2017) for September and October (calculated as difference of midpoint estimates), and Nashant Kishore et al. (May 2018) for December 2017 (blue triangles), and Roberto Rivera and Wolfgang Rolke (Feb. 2018) (red square), and calculated excess deaths using average deaths for 2015 and 2016 compared to 2017 and 2018 using administrative data released 6/1 (black square), and Santos-Lozada estimate based on administrative data released 6/1 (large dark blue triangle), end-of-month figures, all on log scale. + indicate upper and lower bounds for 95% confidence intervals. Orange + denotes Steven Kopits 5/31 estimate for range of excess deaths through September 2018. Cumulative figure for Santos-Lozada and Howard October figure author’s calculations based on reported monthly figures. [Figure revised 6/3]

Continue reading

The Puerto Rico Department of Health has released official data, up to May (May data can be updated, so is as of 6/1).

**Figure 1:** Official death statistics, by month, from Puerto Rico Department of Health. Source.

Given some criticisms of the Harvard School of Public Health led study, published in the *New England Journal of Medicine*, I thought it useful to compare point estimates and 95% confidence intervals of several extant studies, placed in a time context.

**Figure 1:** Estimates from Santos-Lozada and Jeffrey Howard (Nov. 2017) for September and October, and Nashant Kishore et al. (May 2018) for December 2017 (blue triangles), and Roberto Rivera and Wolfgang Rolke (Feb. 2018) (red square), end-of-month figures, all on log scale. + indicate upper and lower bounds for 95% confidence intervals. Cumulative figure for October author’s calculations based on reported monthly figures.

The growth rate of cumulative excess fatalities is in the range of 70% per month.

Steven Kopits has characterized the study published in the *New England Journal of Medicine* as “garbage”, noting that it uses survey data. He has instead relied on Demographic Registry Data in his assessment. He places cumulative excess deaths at 200-400. Interestingly, Rivera and Rolke (2018) also used Demographic Registry Data and concluded that 822 excess deaths occurred from September 20 through October 31 *alone*, with 95% CI (605, 1039). Extrapolating linearly through end-December (time span conforming to the *NEJM* article) would imply 2603 excess deaths, well within the 95% confidence interval of 793-8498.

It should be also remarked upon that the Santos-Lozada and Howard study uses actual statistics for baseline from Puerto Rico Vital Statistics System, and cited numbers processed through Puerto Rico Department of Health for September (extrapolated for October). Hence, this estimate is also not survey based.

Hence, we have two sets of non-survey based estimates that as of October exceed Mr. Kopits’ upper bound of 400.

My op-ed in today’s The Hill:

Is it a trade dispute with China, or is it a trade war? If the latter, is it on hold, or not? The flip-flops in America’s trade relationship with China are coming in ever more frequently, as President Trump issues and rescinds threats.

*Today, we present a guest post written by Jeffrey Frankel, Harpel Professor at Harvard’s Kennedy School of Government, and formerly a member of the White House Council of Economic Advisers. An earlier version appeared in The Hill.
*

Continue reading

Below is reported Economic Policy Uncertainty through 5/31/2018, reflecting newspaper accounts through 5/30.

**Figure 1:** US Economic Policy Uncertainty index (blue) and centered 7-day moving average (bold red). Source: policyuncertainty.com accessed 31 May 2018, and author’s calculations.

As of 2PM EST, Dow down 1%, VIX up 6.69%.