Assessing Uncertainty in Small Area Forecasts: State of the Practice and Implementation Strategy

Forecasts are needed for everyday decisions and must be in the form of numbers. Yet forecasts invariably turn out to be different than the numbers that actually occur. Yet, most producers of forecasts only present a deterministic view of the future in the form of point predictions. However, the presence of uncertainty is inherent in management or policy decisions and there is often concern that benefits are overstated and risks are understated. Such concerns are difficult to address by providing only point forecasts with no assessment of their uncertainty. Having a better understanding of uncertainty can enhance the usefulness of forecasts and make the work of forecasting agencies an even more valuable product for planners, policy makers, and the public. The purpose of this paper is twofold. First, it presents an overview of the current state-of-the-practice is assessing forecast uncertainty. Second, it offers a guidelines and options for implementing and building uncertainty into small area forecasting processes. There are options for assessing forecasting uncertainty that can and should be implemented by most, if not all, producers of forecasts.     

The optimum growth rate for population under critical-level utilitarianism

We characterize optimal consumption, capital, and population growth of a production economy under critical-level utilitarianism. First, we show that neither classical utilitarianism nor average utilitarianism can avoid a corner solution for the population growth rate, in that under the former, population grows at the maximum speed (the so-called repugnant conclusion) while under the latter, it grows at the minimum. Second, we show that critical level utilitarianism yields an interior solution for the population growth rate provided the critical level belongs to a positive, open interval. Finally, we characterize the transition to the steady state and perform comparative dynamics analysis.     

Life test sampling plans for Weibull distributed lifetimes under accelerated hybrid censoring

Life test sampling plans (LSPs) for the Weibull distribution are usually developed under the assumptions that the shape parameter is known and the life test is conducted at an accelerated condition for which the acceleration factor (AF) is known. However, the sensitivities of a plan to the assumed shape parameter and AF have been rarely investigated. This paper considers the case where the life test is hybrid censored and develops attributes LSPs under the above assumptions. Then, sensitivity analyses are conducted to assess the effects of the uncertainties in the assumed AF and shape parameter on the actual producer and consumer risks. A method is also developed for constructing LSPs that can accommodate these uncertainties.     

Interval shrinkage estimators

This paper considers estimation of an unknown distribution parameter in situations where we believe that the parameter belongs to a finite interval. We propose for such situations an interval shrinkage approach which combines in a coherent way an unbiased conventional estimator and non-sample information about the range of plausible parameter values. The approach is based on an infeasible interval shrinkage estimator which uniformly dominates the underlying conventional estimator with respect to the mean square error criterion. This infeasible estimator allows us to obtain useful feasible counterparts. The properties of these feasible interval shrinkage estimators are illustrated both in a simulation study and in empirical examples.     

On a problem with singularity in comparison of linear experiments

For consistency, the parameter space in the Gauss-Markov model with singular covariance matrix is usually restricted by observation vector. This restriction arises some difficulties in comparison of linear experiments. To avoid it we reduce the problem of comparison from singular to nonsingular case.     

An information-theoretic approach to surrogate-marker evaluation with failure time endpoints

Over the last decades, the evaluation of potential surrogate endpoints in clinical trials has steadily been growing in importance, not only thanks to the availability of ever more potential markers and surrogate endpoints, also because more methodological development has become available. While early work has been devoted, to a large extent, to Gaussian, binary, and longitudinal endpoints, the case of time-to-event endpoints is in need of careful scrutiny as well, owing to the strong presence of such endpoints in oncology and beyond. While work had been done in the past, it was often cumbersome to use such tools in practice, because of the need for fitting copula or frailty models that were further embedded in a hierarchical or two-stage modeling approach. In this paper, we present a methodologically elegant and easy-to-use approach based on information theory. We resolve essential issues, including the quantification of “surrogacy” based on such an approach. Our results are put to the test in a simulation study and are applied to data from clinical trials in oncology. The methodology has been implemented in R.     

A joint-modeling approach to assess the impact of biomarker variability on the risk of developing clinical outcome

In some clinical trials and epidemiologic studies, investigators are interested in knowing whether the variability of a biomarker is independently predictive of clinical outcomes. This question is often addressed via a naïve approach where a sample-based estimate (e.g., standard deviation) is calculated as a surrogate for the “true” variability and then used in regression models as a covariate assumed to be free of measurement error. However, it is well known that the measurement error in covariates causes underestimation of the true association. The issue of underestimation can be substantial when the precision is low because of limited number of measures per subject. The joint analysis of survival data and longitudinal data enables one to account for the measurement error in longitudinal data and has received substantial attention in recent years. In this paper we propose a joint model to assess the predictive effect of biomarker variability. The joint model consists of two linked sub-models, a linear mixed model with patient-specific variance for longitudinal data and a full parametric Weibull distribution for survival data, and the association between two models is induced by a latent Gaussian process. Parameters in the joint model are estimated under Bayesian framework and implemented using Markov chain Monte Carlo (MCMC) methods with WinBUGS software. The method is illustrated in the Ocular Hypertension Treatment Study to assess whether the variability of intraocular pressure is an independent risk of primary open-angle glaucoma. The performance of the method is also assessed by simulation studies.     

Corporate divestiture and performance: an institutional view

In this study, we investigate how the institutional environment affects shareholders’ reaction to a firm’s announcement of divestitures. Traditionally, divestiture research has adhered to a financial economics perspective, in which shareholders anticipate certain economic outcomes from corporate divestitures and react accordingly. However, this research has not delivered a distinct understanding of the performance effects of corporate divestitures. To structure and integrate previous work, we apply a neo-institutional perspective of the stock market. We argue that at certain times, the institutional support for corporate diversification is relatively low. During these periods, there is a high rate of divestitures. The high divestiture activity legitimizes this corporate action and leads to a positive reaction of the stock market to new divestiture announcements. This means that individual evaluations of the possible performance outcomes of divestments are not the only factor determining the stock market reaction to a corporate divestiture announcement. Rather, investors might consider the perceived institutionalization of this corporate action when making their purchasing decisions. Using a meta-analytical technique, we find support for our prediction that different performance effects of divestitures, as revealed by previous studies, can be attributed to different conditions of the macro-economic environment. We discuss the implications of this result for research and management practice.     

Job-related diversity: the comprehensiveness and speed of board decision-making processes—an upper echelons approach

Strategic decision-making processes influence firm-level outcomes. Using the theory of upper echelons, this study investigates how diversity in directors’ skills, knowledge, and industry experience influence board decision-making processes that may impact overall strategic decision-making processes. Such diversity has been commonly accepted to be a ‘double-edged sword’—enhancing comprehensiveness but hindering the speed of decision-making. On the contrary, we used an existing large survey database to show that directors’ diverse educational background, functional background, and industry experience (job-related diversity) have a positive effect on comprehensiveness as well as the speed of board decision-making. In addition, our results indicate that board processes (directors’ use of their knowledge and skills) play an important role by transmitting the positive effects of diversity. The study is in a tradition of exploring how boards may influence firms’ strategic decision-making processes. Our findings provide additional arguments for adding job-related diversity to boards of directors.