Asymptotic distributions of kappa statistics and their differences with many raters,many rating categories and two conditions

In clinical research and in more general classification problems, a frequent concern is the reliability of a rating system. In the absence of a gold standard, agreement may be considered as an indication of reliability. When dealing with categorical data, the well‐known kappa statistic is often used to measure agreement. The aim of this paper is to obtain a theoretical result about the asymptotic distribution of the kappa statistic with multiple items, multiple raters, multiple conditions, and multiple rating categories (more than two), based on recent work. The result settles a long lasting quest for the asymptotic variance of the kappa statistic in this situation and allows for the construction of asymptotic confidence intervals. A recent application to clinical endoscopy and to the diagnosis of inflammatory bowel diseases (IBDs) is shortly presented to complement the theoretical perspective.     

Priors for the Bayesian star paradox

We show that the Bayesian star paradox, first proved mathematically by Steel and Matsen for a specific class of prior distributions, occurs in a wider context including less regular, possibly discontinuous, prior distributions.     

Power analysis of statistical methods for comparing treatment differences from limiting dilution assays

Summary Six different statistical methods for comparing limiting dilution assays were evaluated, using both real data and a power analysis of simulated data. Simulated data consisted of a series of 12 dilutions for two treatment groups with 24 cultures per dilution and 1,000 independent replications of each experiment. Data within each replication were generated by Monte Carlo simulation, based on a probability model of the experiment. Analyses of the simulated data revealed that the type I error rates for the six methods differed substantially, with only likelihood ratio and Taswell's weighted mean methods approximating the nominal 5% significance level. Of the six methods, likelihood ratio and Taswell's minimum Chi-square exhibited the best power (least probability of type II errors). Taswell's weighted mean test yielded acceptable type I and type II error rates, whereas the regression method was judged unacceptable for scientific work.     

The genetic structure of a tribal population,the Yanomama Indians. XII. Biodemographic studies

The Yanomama Indians of Southern Vanezuela and Northern Brazil are one of the largest, relatively unacculturated tribes of the tropical rain forest. Over a period of eight years data have been collected from a considerable portion of their territory on estimated age, sex ratio, fertility rates (as determined by physical examination and urine tests), and infant death rates. Although it has been impossible to collect direct data on infanticide, this subject can be approached indirectly through distortions of the sex ratio and anecdotal information. Some historical data are also available as a basis for estimating tribal expansion in the past 100 years. With this material it has been possible to construct Life Tables for the Yanomama, and to explore the results of various perturbations of the input parameters. Data are also presented on patterns of mating and reproduction: number of spouses, mean and variance in number of surviving children, frequency of “extra-marital conceptions” based on the results of extensive blood group typings, and consanguinity rates as determined by observation and computer simulation. Although we do not present the Yanomama as typical, these data are seen as providing a basis for more realistic population models than have existed in the past. In addition, the data provide a basis for relatively precise estimates of such demographic measures as Fisher's Reproductive Value, Crow's Index of Total Selection, and Weiss' Index of Growth Regulation.     

Correction of a bootstrap approach to testing for evolution along lines of least resistance

Testing for an association between the leading vectors of multivariate trait (co)variation within populations (the ‘line of least resistance’) and among populations is an important tool for exploring variational bias in evolution. In a recent study of stickleback fish populations, a bootstrap‐based test was introduced that takes into account estimation error in both vectors and hence improves the previously available bootstrap method. Because this test was implemented incorrectly, however, I here describe the correct test protocol and provide a reanalysis of the original data set. The application of this new test protocol should improve future investigations of evolution along lines of least resistance and other vector comparisons.     

Basic data standards for primate colonies

A set of simple standards has been developed to ease the task of transferring primate colony data between institutions and computers, and to assure that colony vital statistics are appropriate for demographic and genetic analyses. The standards have been designed to be easily and inexpensively implemented from existing databases, and also may serve as a guide to the setup of new colony record-keeping systems. © 1993 Wiley-Liss, Inc.     

The Distribution of the Number of Maxima in a Cyclic Sequence

A simple statistical method is presented which tests for non-randomness in a cyclic sequence. The distribution of the statistic is tabulated for short sequences, and a large sample approximation is derived. Significant values of the statistic are given for sequences of length up to 52. Easily used computer programs to carry out appropriate calculations are presented.