Dennis Lindley, one of the most influential of 20th century statisticians, passed away on December 14 at age 90. Lindley was a strong advocate for Bayesian statistics before it was widely popular. What is Bayesian statistics and why was Dennis Lindley important? [more inside]
Statistical hypothesis testing with a p-value of less than 0.05 is often used as a gold standard in science, and is required by peer reviewers and journals when stating results. Some statisticians argue that this indicates a cult of significance testing using a frequentist statistical framework that is counterintuitive and misunderstood by many scientists. Biostatisticians have argued that the (over)use of p-vaues come from "the mistaken idea that a single number can capture both the long-run outcomes of an experiment and the evidential meaning of a single result" and identify several other problems with significance testing. XKCD demonstrates how misunderstandings of the nature of the p-value, failure to adjust for multiple comparisons, and the file drawer problem result in likely spurious conclusions being published in the scientific literature and then being distorted further in the popular press. You can simulate a similar situation yourself. John Ioannidis uses problems with significance testing and other statistical concerns to argue, controversially, that "most published research findings are false." Will the use of Bayes factors replace classical hypothesis testing and p-values? Will something else?
The Marquis de Condorcet and Admiral Jean-Charles de Borda were two men of the French Enlightenment who struggled with how to design voting systems that accurately reflected voters' preferences. Condorcet favored a method that required the winner in a multiparty election to win a series of head-to-head contests, but he also discovered that his method easily led to a paradoxes that produced no clear winners. The Borda method avoids the Condorcet paradox by requiring voters to rank choices numerically in order of preference, but this method is flawed because the withdrawal of a last-place candidate can reverse the election results. Mathematicians in the 19th century attempted to design better voting systems, including Lewis Carroll, who favored an early form of proportional representation. Economist Kenneth Arrow argued that designing a perfect voting system was futile, because his "impossibility theorem" proved that it's impossible to design a non-dictatorial voting system that fulfills five basic criteria of fairness. (more inside)
Odds are, God exists. So says Dr. Stephen Unwin, a risk assessor in Ohio who applied Bayes' Theory to the question and determined there's a 67% likelihood of ... you-have-to-buy-the-book-to-find-out. Ah, the Devil is in the retail -- er, I mean, the details. As a scientist and a Christian, I'm embarrassed by this junk. His book "includes a spreadsheet of the data used so that anyone can make the calculation themselves should they doubt its validity." I can hardly wait.