Only 7 census tracts in Washington, DC are identified as "food deserts." In one case, the reason is not a lack of access so much as the government's cramped definition of an acceptable grocery store. In one other case, the reason is the government's definition disregards large grocery stores in adjacent census tracts that lie within one mile of where people actually live. For the remaining five census tracts, no large grocery stores appear to be nearby under any reasonable definition of the term. But these census tracts are predominantly industrial.
Yesterday's post on the federal government's new program to eradicate "food deserts" provided an obvious example in which the database yields nonsensical results. A large US Army installation, one with its own grocery store, no unemployment, and essentially no poverty, nevertheless appeared to meet all of the government's (arbitrary) criteria for inclusion.
A closer look shows that there is yet another reason why this particular "food desert" is a mirage. Soldiers who live within this census tract actually do live within one mile of a second, large grocery store--albeit one that is in an adjacent census tract.
One of the latest trends in federal government food policy is the eradication of "food deserts" -- places where it is said to be difficult to find fresh produce. The Economic Research Service of the US Department of Agriculture has created an interactive map to help you learn whether you live in a "food desert".
The data are interesting, but perhaps not for the intended reason.
The Report of the Comprehensive Review of the Issues Associated with a Repeal of 'Don't Ask, Don't Tell' was released by the Department of Defense on November 30, 2010. The Report summarizes and interprets a pair of large-scale surveys of Service members and spouses hat was sponsored by DoD and conducted by WESTAT, a major consulting firm. Immediately thereafter, Congress took up the question whether to repeal the law on which the Department's "Don't Ask, Don't Tell" policy is based.
This post is about the Report's statistical back story, and why the conclusions given in the Report are unreliable as a guide for policy-making -- regardless of whether one prefers to repeal the law, retain the law, or replace it with a more stringent one. More...
Estimating the quantity of something that does not want to be estimated could be the most difficult quantitative task around. For this reason, estimates of the unlawful alien population are prone to both error and bias.
The Pew Hispanic Center published new estimates on September 1. Pew's estimates are reported as being much more certain than they actually are.
The federal government's reported figures for jobs "created or saved" by the "stimulus" bill (formally the American Recovery and Reinvestment Act of 2009, or "ARRA") are now known to be wrong. The Recovery Accountability and Transparency Board, which oversees these figures, apparently has decided not to correct them.
A scandal has erupted over the federal government's reporting of the number of jobs created or saved by the "stimulus" bill (formally the American Recovery and Reinvestment Act of 2009).
This scandal would have been avoided if the government had complied with the Information Quality Act.
The US Preventive Services Task Force issued a report with revised recommendations calling for much less frequent use of mammograms for screening women with no risk factors for breast cancer. The announcement triggered an extraordinary reaction, most of which was negative.
Few of those reacting had actually read the report. In many cases, the complaints were factually inaccurate -- by that we mean they objected to things that were not in the report.
California is at the vanguard of pricing electricity by the time of day it is used. The reason is that it costs more to produce (or buy) electricity at peak times. By charging prices linked to marginal cost, electricity consumers can be motivated to use power when it is less expensive.
The movement toward marginal cost pricing is encountering opposition.
The Associated Press reports from Afghanistan on how the UN-backed Electoral Complaints Commission will adjust vote totals to account for fraud, which now appears to have been widespread in the August 20, 2009, presidential election. The EEC is sampling ballots to determine the number and rate of fraudulent votes for each candidate. It appears that it has chosen an adjustment method that rewards fraud.
Wall Street Journal's "Numbers Guy" Carl Bialik writes in an August 7 blog post about the claim made by Sky Andrecheck that baseball would be no different if the numbers of balls and strikes were reduced to three and two, respectively:
Specifically, writing on Baseball Analysts, [Andrecheck] presents data suggesting that a game where three balls earned a batter a walk but two strikes ends his at bat would have very similar outcomes to what we know as baseball, but get to those outcomes a lot faster — and with fewer pitching changes.
Andrecheck commits an elementary statistical error and he incorrectly assumes that at-bat data are true.
The Panic of 2008 and subsequent recession have put a damper on the wine market, especially at the high end. As a member of too many wine clubs (still the best way to access fine West Coast wine from the East Coast), I have seen more discounting by wineries in the last six months than I observed in the previous six years.
So it should not be surprising to see a bevy of entrepreneurs pop up who are attempting to exploit these depressed conditions. The Los Angeles Times published an intriguing story by reporter Patrick Comiskey about new web-based vendors doing exactly what we'd expect ("Good deals go fast on wine websites," July 8, 2009). Of the vendors Comiskey mentions, Wines 'Til Sold Out seems to have the most unusual business plan: they sell tranches of a single wine, one at a time, first come first served, presumably (but not verifiably) until they are sold out -- then move on to another wine.
After reading the article, I signed up with Wines 'Til Sold Out to investigate.
On June 11 the World Health Organization decreed that the recent outbreak of (A)H1N1 influenza ("swine flue") qualified as a "pandemic." According to reporters for the Washington Post, WHO delayed making this decision long after it technically met its established definition. The reason for delay is that policy officials no longer liked the definition and were concerned that a declaration of a pandemic could lead to panic.
In recent years there has been a notable increase in the use of expert elicitation in human health risk assessment. The method usually involves empaneling a group of experts and, through a carefully crafted and complex set of procedures, asking each panel member to provide a subjective probability that some phenomenon that cannot be directly observed is true or false. The Environmental Protection Agency has an informative external review draft white paper on the subject.
In environmental health, expert elicitation has been used to quantify the risk of cancer from drinking water disinfection byproducts, the likelihood that routine exposure to particulate matter in air causes premature mortality, and the magnitude of uncertainties related to climate change. Each is a tough scientific question. For example, the risk involved may be quantitatively small, and hence hard to discern, or the scientific uncertainties may be very large. Judgment is required, and the judgments of scientists inevitably reflect a mixture of scientific expertise and nonscientific opinion.
The need for discerning science from policy in expert judgment has been recognized for decades, at least since the 1983 National Research Council Red Book. No consensus yet exists concerning how to do this in practice. As a result, practitioners of expert elicitation typically acknowledge the problem but not much else. The EPA external review draft white paper mentioned above, for example, says that Agency technical support documents relying on expert elicitation should address "[p]ossible correlations with non-elicited components of the overall analysis or policy question" -- a phrase that, when translated into plain English, means the inflitration of experts' policy views into their characterization of science.
Today's Wall Street Journal has an example drawn from a very different arena -- macroeconomic forecasting -- that offers a wealth of insight about the problems with expert elicitation.
