Generalizing the standardized hazard ratio to multivariate proportional hazards regression,with an application to clinical~genomic studies

The standardized hazard ratio for univariate proportional hazards regression is generalized as a scalar to multivariate proportional hazards regression. Estimators of the standardized log hazard ratio are developed, with corrections for bias and for regression to the mean in high-dimensional analyses. Tests of point and interval null hypotheses and confidence intervals are constructed. Cohort sampling study designs, commonly used in prospective–retrospective clinical genomic studies, are accommodated.     

Differential customer racial attitudes toward scandal and patriotism: The Mitchell Report,the Olympics,race, and baseball memorabilia

This paper investigates differential customer racial reaction to negative and positive publicity related to professional athletes. In terms of negative publicity, it analyzes the effect of mention in the Mitchell Report on the price of baseball cards. In regards to positive publicity, it considers the impact of having been identified as a member of the United States Olympic or national team. After controlling for player productivity with performance statistics, the effects of being mentioned in the Mitchell Report are isolated within regression analysis to draw conclusions concerning customer racial attitudes toward the steroids scandal. Similar analysis is conducted to see the impact of being seen as a baseball representative of the United States. Regression results are consistent with the conclusion that negative publicity devalues the cards of nonWhite players but not of White players. Positive publicity, however, increases the value of a player's card regardless of ethnicity.     

Q-LEARNING WITH CENSORED DATA

We develop methodology for a multistage-decision problem with flexible number of stages in which the rewards are survival times that are subject to censoring. We present a novel Q-learning algorithm that is adjusted for censored data and allows a flexible number of stages. We provide finite sample bounds on the generalization error of the policy learned by the algorithm, and show that when the optimal Q-function belongs to the approximation space, the expected survival time for policies obtained by the algorithm converges to that of the optimal policy. We simulate a multistage clinical trial with flexible number of stages and apply the proposed censored-Q-learning algorithm to find individualized treatment regimens. The methodology presented in this paper has implications in the design of personalized medicine trials in cancer and in other life-threatening diseases.     

The Box–Cox Transformation and Non‐Iterative Estimation Methods for Ordinal Log‐Linear Models

Recently Beh and Farver investigated and evaluated three non‐iterative procedures for estimating the linear‐by‐linear parameter of an ordinal log‐linear model. The study demonstrated that these non‐iterative techniques provide estimates that are, for most types of contingency tables, statistically indistinguishable from estimates from Newton's unidimensional algorithm. Here we show how two of these techniques are related using the Box–Cox transformation. We also show that by using this transformation, accurate non‐iterative estimates are achievable even when a contingency table contains sampling zeros.     

For compassion or money? The factors influencing the funding of micro loans

Aided by the Internet, microfinance institutions have found new ways to expand the reach of financing entrepreneurial projects on a small scale. Using a unique data set of individual loans posted to Kiva.org, we explore the determinants of lenders’ nonprofit lending choices in the growing microfinance industry. We find that lenders make choices in purposive ways even in the absence of market interest rates, especially with respect to the demographic characteristics of borrowers and the uses of proposed funds. Hence, the results provide valuable new information about consumer choice in charitable giving and investment.     

The ensemble Kalman filter is an ABC algorithm

The ensemble Kalman filter is the method of choice for many difficult high-dimensional filtering problems in meteorology, oceanography, hydrology and other fields. In this note we show that a common variant of the ensemble Kalman filter is an approximate Bayesian computation (ABC) algorithm. This is of interest for a number of reasons. First, the ensemble Kalman filter is an example of an ABC algorithm that predates the development of ABC algorithms. Second, the ensemble Kalman filter is used for very high-dimensional problems, whereas ABC methods are normally applied only in very low-dimensional problems. Third, recent state of the art extensions of the ensemble Kalman filter can also be understood within the ABC framework.     

The Impact of Macro- and Micro-Economic Uncertainty on Family Formation in The Netherlands

In this paper, we study the impact of macro- and micro-economic uncertainty on family formation between 1970 and 2000 in The Netherlands. Using data of the Family Survey Dutch Population, we analysed the monthly hazard rates of experiencing the transition into first union, first marriage and parenthood after the start of the relationship of 365 male and 364 female partners by applying piecewise-constant exponential models. The results show that macro-economic uncertainties, i.e. high unemployment rates, lead to postponement of the first union and marriage, but not of the first child. In addition, we found that this relationship is not interpreted by individual-level employment insecurity, i.e. temporary employment or unemployment, which does not seem to prevent people from making long-term family commitments. Although hypothesized, we did not find that the negative effects of macro- and micro-level insecurities on family formation reinforce each other or that they vary between individuals with different educational qualifications.     

SOS—Satisfied or Stuck,Why Older Rural Residents Stay Put: Aging in Place or Stuck in Place in Rural Utah*

As rural communities undergo substantial demographic and economic changes, understanding the migration intentions and their antecedents of rural elderly persons becomes increasingly important. Using data drawn from a survey of adults from 24 rural Utah communities conducted in 2008, we examine whether rural residents 60 years of age or older plan to remain in their present communities (N= 621). We use structural equation models (SEM) to estimate the relationships between a variety of individual and community-level background measures, including perceptions of local service quality, leaving one's community for health care, Internet use, attachment to and satisfaction with community, and plans to age in place. Results suggest that even as the rural context of economic decline, population loss, and distance to medical services may reduce the viability of staying in a community, a desire to remain in the community is primarily a function of perceptions of the quality of local services and community satisfaction. This research highlights the need to better understand the interplay between the availability of medical services and perceptions of distance as well as to understand the complex relationship between individual and community level characteristics for migration intentions.