Individual-level loss aversion in riskless and risky choices

Theory and Decision - Loss aversion can occur in riskless and risky choices. We present novel evidence on both in a non-student sample (660 randomly selected customers of a car manufacturer). We...     

Performance of Variable Selection Methods in Regression Using Variations of the Bayesian Information Criterion

The Bayesian information criterion (BIC) is widely used for variable selection. We focus on the regression setting for which variations of the BIC have been proposed. A version that includes the Fisher Information matrix of the predictor variables performed best in one published study. In this article, we extend the evaluation, introduce a performance measure involving how closely posterior probabilities are approximated, and conclude that the version that includes the Fisher Information often favors regression models having more predictors, depending on the scale and correlation structure of the predictor matrix. In the image analysis application that we describe, we therefore prefer the standard BIC approximation because of its relative simplicity and competitive performance at approximating the true posterior probabilities.     

Performance and Prediction for Varying Survival Time Scales

The Cox proportional hazards model is widely used for analyzing associations between risk factors and occurrences of events. One of the essential requirements of defining Cox proportional hazards model is the choice of a unique and well-defined time scale. Two time scales are generally used in epidemiological studies: time-on-study and chronological age. The former is the most frequently used time scale, both in clinical studies and longitudinal observation studies. However, there is no general consensus on which time scale is the most appropriate for a given question or study. In this article, we address the question of robustness of the results using one time scale when the other is actually the correct one. We use three criteria to measure the performances of these models through simulations: magnitude of the bias of the regression coefficients, mean square errors, and the measure of overall predictive discrimination of the models. We conclude that the time-on-study models are more robust to misspecification of the underlying time scale.     

Quasi-Likelihood Approach to Bioavailability and Bioequivalence Analysis

The outcomes AUCT (area-under-curve from time zero to time t) of n individuals randomized to one of two groups TR or RT, where the group name denotes the order in which the subjects receive a test formulation (T) or a reference formulation (R), are used to assess average bioequivalence for the two formulations. The classical method is the mixed model, for example, proc mixed or proc glm with random statement in SAS can be used to analyze this type of data. This is equivalent to the marginal likelihood approach in a normal–normal model. There are some limitations for this approach. It is not appropriate if the random effect is not normally distributed. In this article, we introduce a hierarchical quasi-likelihood approach. Instead of assuming the random effect is normal, we make assumptions only about the mean and the variance function of the random effect. Our method is flexible to model the random effect. Since we can estimate the random effect for each individual, we can check the adequacy of the distribution assumption about the random effect. This method can also be used to handle high-dimensional crossover data. Simulation studies are conducted to check the finite sample performance of the method under various conditions and two real data examples are used for illustration.     

Correspondence Analysis of Cumulative Frequencies Using a Decomposition of Taguchi's Statistic

Taguchi's statistic has long been known to be a more appropriate measure of association for ordinal variables than the Pearson chi-squared statistic. Therefore, there is some advantage in using Taguchi's statistic for performing correspondence analysis when a two-way contingency table consists of one ordinal categorical variable. This article will explore the development of correspondence analysis using a decomposition of Taguchi's statistic.     

Should Macroeconomic Forecasters Use Daily Financial Data and How?

We introduce easy-to-implement, regression-based methods for predicting quarterly real economic activity that use daily financial data and rely on forecast combinations of mixed data sampling (MIDAS) regressions. We also extract a novel small set of daily financial factors from a large panel of about 1000 daily financial assets. Our analysis is designed to elucidate the value of daily financial information and provide real-time forecast updates of the current (nowcasting) and future quarters of real GDP growth.     

Calculating Bivariate Orthonormal Polynomials By Recurrence

Emerson gave recurrence formulae for the calculation of orthonormal polynomials for univariate discrete random variables. He claimed that as these were based on the Christoffel–Darboux recurrence relation they were more efficient than those based on the Gram–Schmidt method. This approach was generalised by Rayner and colleagues to arbitrary univariate random variables. The only constraint was that the expectations needed are well‐defined. Here the approach is extended to arbitrary bivariate random variables for which the expectations needed are well‐defined. The extension to multivariate random variables is clear.     

The Great Emigration of 1841: Recruitment for New South Wales in British Emigration Fields

A survey of papers reporting the use of ethnographies in three population journals and an examination of two case studies show that the criticisms made by anthropologists and others of demographers’ use of ethnographies are well founded. In their use of these accounts, demographers tend to present an excessively static view of social organization, to use ethnographic evidence selectively to support other findings, to be indifferent to how long ago an ethnography was produced, to take for granted the validity of the ethnographic evidence, to ignore the broader historical context in which the ethnography was produced, and to be unaware of the ways in which demographic evidence can be used at all stages of the research process. The adoption of anthropologists’ suggestions for establishing the plausibility and credibility of ethnographic evidence could improve the value of the contribution made by these studies to demographic research and theory.     

Comments on “Unbiased estimates for moments and cumulants in linear regression”

In a recent number of the Journal of Statistical Planning and Inference, a short communication by Withers and Nadarajah (2011) on the unbiased estimation of the moments and cumulants for linear regression models was published. However, some of the results presented in this paper, as well as those closely related, were partially obtained in other works, which were not referenced or were referenced in other contexts. In addition, the consistency of the derived estimates was not studied. The aim of these short comments is to briefly present these results, as well as some omitted works, in order to give larger representation of the state of art in this field.