Nonstationarity and Level Shifts With an Application to Purchasing Power Parity

This study considers testing for a unit root in a time series characterized by a structural change in its mean. The analysis is in the spirit of Perron (1990a), who showed that the existence of such a shift in a stationary time series biases the usual tests for a unit root toward nonrejection. The approach is, however, different given that we suppose the date of the change to be unknown. The statistic of interest is then the minimal t statistic over all possible breakpoints in regressions similar to those proposed by Perron (1990a). Other related statistics are also discussed. We derive and tabulate the asymptotic distributions of interest. Most of the emphasis, however, is given to the tabulation of finite-sample critical values using simulation experiments. Particular attention is given to the effect, on the finite-sample critical values, of various procedures to select the appropriate order of the estimated autoregressions. We apply the tests to analyze the issue of purchasing power parity between the United States and the United Kingdom and also between the United States and Finland, whose real exchange rates are characterized by apparent shifts in level when using particular price indexes.     

Socioeconomic determinants of the need for personal assistance reported by community-dwelling elderly: Empirical evidence from a French national health survey

A bivariate probit model with sample selection is used to estimate the conditional probability of reporting a need for personal assistance (NPA) with at least one activity of daily living among French community-dwelling elderly. 71.8% of men and 77.3% of women reported impairments and among those who reported impairments, 7.5% of men and 10.8% of women reported NPA. NPA is associated not only with age (i.e., the oldest individuals, for women only) and health status (such as a specific type of impairment), but also with socioeconomic (living with intermediate income; living with someone, partner or other) and environmental factors (having and using assistive technologies).     

Utility values in health technology assessments: a statistician's perspective

This paper provides an introduction to utilities for statisticians working mainly in clinical research who have not had experience of health technology assessment work. Utility is the numeric valuation applied to a health state based on the preference of being in that state relative to perfect health. Utilities are often combined with survival data in health economic modelling to obtain quality‐adjusted life years. There are several methods available for deriving the preference weights and the health states to which they are applied, and combining them to estimate utilities, and the clinical statistician has valuable skills that can be applied in ensuring the robustness of the trial design, data collection and analyses to obtain and handle this data. In addition to raising awareness of the subject and providing source references, the paper outlines the concepts and approaches around utilities using examples, discusses some of the key issues, and proposes areas where statisticians can collaborate with health economic colleagues to improve the quality of this important element of health technology assessment. Copyright © 2014 John Wiley & Sons, Ltd.     

Randomize groups, not individuals: a strategy for improving early childhood programs

Until the past few years, our nation's approach to designing federal programs for preschool-age children lacked coherence and paid little attention to what had worked (and not worked) in the past. In this article, the authors propose that credible information useful for designing effective programs will require the ongoing, systematic development and evaluation of alternative approaches for the improvement of large-scale early childhood programs. The research should place greater reliance on experiments in which existing groups of individuals, such as intact classes or preschool agencies, are randomly assigned to implement competing early education programs or program components. Randomizing groups, rather than individual children, changes the research question from "What works?" to "What works better?" yielding more useful information than is currently available about which preschool approaches ought to be strongly embedded in our nation's social policy.     

Approximate Bayesian computational methods

Approximate Bayesian Computation (ABC) methods, also known as likelihood-free techniques, have appeared in the past ten years as the most satisfactory approach to intractable likelihood problems, first in genetics then in a broader spectrum of applications. However, these methods suffer to some degree from calibration difficulties that make them rather volatile in their implementation and thus render them suspicious to the users of more traditional Monte Carlo methods. In this survey, we study the various improvements and extensions brought on the original ABC algorithm in recent years.     

On the Deng-Lin random number generators and related methods

We study the structure and point out weaknesses of recently proposed random number generators based on special types of linear recurrences with small coefficients, which allow fast implementations. Our theoretical analysis is complemented by the results of simple empirical statistical tests that the generators fail decisively. Directions for improvement and alternative generators are also pointed out.     

An evaluation of the nutrition education and training program : Findings from Nebraska

This paper summarizes methods and findings from a classical randomized experiment used to evaluate the Nutrition Education and Training (NET) Program that was developed and implemented in Nebraska. The evaluation focused on assessing how well the program was implemented and the impact it had on children's nutrition-related knowledge, attitudes, preferences, and habits. Data were collected from over 2,300 children in 96 classrooms distributed across grades 1–6 in 20 schools spanning the state of Nebraska. The 20 participating schools were selected from 98 volunteers and were assigned to treatment or control status using a modified random assignment procedure that resulted in equivalent pretest means on outcome measures. Pretest data and two waves of posttest data were collected. The evaluation found strong positive effects in all grades on several measures of nutrition knowledge, positive effects on reported food preference and willingness to select new foods in the school lunch line in grades 1–3, positive effects on willingness to taste previously rejected foods in grades 4–6, and no consistent effects on food attitudes, reported food habits, or plate waste.     

Analysing and reducing customer defections

Firms can grow businesses by attracting new customers, losing fewer customers and doing more business with existing customers. Keeping your present customers and doing more business with them is generally a more efficient way of using resources. It requires a detailed analysis of customer defections to assess the effects of losing customers on long-term profitability and growth. This article provides some simple but powerful graphical analysis tools to use in customer defections analysis. The tools are initially described using the simple case of a service firm to show how managers can examine the probability of defections and the resulting need to attract new customers. Then the techniques are illustrated graphically using data from a UK subsidiary of an American concern which supplies equipment to large organizations. The analysis of customer defections is summarized in a sixstage process.     

How French industry plans

This paper presents briefly the results of an empirical study on long-range forecasting conducted in large French corporations. It demonstrates that forecasting differs quite widely according to its technical, economic or social nature.