Power of the Neyman Smooth Test for Evaluating Multivariate Forecast Densities

We compare and investigate Neyman's smooth test, its components, and the Kolmogorov-Smirnov (KS) goodness-of-fit test for testing the uniformity of multivariate forecast densities. Simulations indicate that the KS test lacks power when the forecast distributions are misspecified, especially for correlated sequences of random variables. Neyman's smooth test and its components work well in samples of size typically available, although there sometimes are size distortions. The components provide directed diagnosis regarding the kind of departure from the null. For illustration, the tests are applied to forecast densities obtained from a bivariate threshold model fitted to high-frequency financial data.     

Principles for Conduct of Pest Risk Analyses: Report of an Expert Workshop

The North American Free Trade Agreement (NAFTA) and the General Agreement on Tariffs and Trade (GATT) have focused attention on risk assessment of potential insect, weed, and animal pests and diseases of livestock. These risks have traditionally been addressed through quarantine protocols ranging from limits on the geographical areas from which a product may originate, postharvest disinfestation procedures like fumigation, and inspections at points of export and import, to outright bans. To ensure that plant and animal protection measures are not used as nontariff trade barriers, GATT and NAFTA require pest risk analysis (PRA) to support quarantine decisions. The increased emphasis on PRA has spurred multiple efforts at the national and international level to design frameworks for the conduct of these analyses. As approaches to pest risk analysis proliferate, and the importance of the analyses grows, concerns have arisen about the scientific and technical conduct of pest risk analysis. In January of 1997, the Harvard Center for Risk Analysis (HCRA) held an invitation-only workshop in Washington, D.C. to bring experts in risk analysis and pest characterization together to develop general principles for pest risk analysis. Workshop participants examined current frameworks for PRA, discussed strengths and weaknesses of the approaches, and formulated principles, based on years of experience with risk analysis in other setting and knowledge of the issues specific to analysis of pests. The principles developed highlight the both the similarities of pest risk analysis to other forms of risk analysis, and its unique attributes.     

Modelling step-families

A combined marco-micro model is applied to a population similar to that forecast for 2035 in the Netherlands in order to simulate the effect on kinship networks of a mating system of serial monogamy. The importance of incorporating a parameter for the degree of concentration of childbearing over the female population is emphasized. The inputs to the model are vectors of fertility rates by age of mother, and by age of father, a matrix of first-marriage rates by age of both partners (used in the macro-analytical expressions), and two parametersH andS (used in the micro-simulation phase). The output is a data base of hypothetical individuals, whose records contain identification number, age, sex, and the identification numbers of their relatives.     

Lower posterior death probabilities from a quick medical response in road traffic accidents

Introduction: We use data from Spain on roads and motorways traffic accidents in May 2004 to quantify the statistical association between quick medical response time and mortality rate. Method: Probit and logit parameters are estimated by a Bayesian method in which samples from the posterior densities are obtained through an MCMC simulation scheme. We provide posterior credible intervals and posterior partial effects of a quick medical response at several time levels over which we express our prior beliefs. Results: A reduction of 5 min, from a 25-min response-time level, is associated with lower posterior probabilities of death in roads and motorways accidents of 24% and 30%, respectively.     

Hypothesis test for paired samples in the presence of missing data

Missing data are present in almost all statistical analysis. In simple paired design tests, when some subject has one of the involved variables missing in the so-called partially overlapping samples scheme, it is usually discarded for the analysis. The lack of consistency between the information reported in the univariate and multivariate analysis is, perhaps, the main consequence. Although the randomness on the missing mechanism (missingness completely at random) is an usual and needed assumption for this particular situation, missing data presence could lead to serious inconsistencies on the reported conclusions. In this paper, the authors develop a simple and direct procedure which allows using the whole available information in order to perform paired tests. In particular, the proposed methodology is applied to check the equality among the means from two paired samples. In addition, the use of two different resampling techniques is also explored. Finally, real-world data are analysed.     

A time-varying measurement error model for age of onset of a psychiatric diagnosis: applied to first depressive episode diagnosed by the Composite International Diagnostic Interview (CIDI)

A substantial degree of uncertainty exists surrounding the reconstruction of events based on memory recall. This form of measurement error affects the performance of structured interviews such as the Composite International Diagnostic Interview (CIDI), an important tool to assess mental health in the community. Measurement error probably explains the discrepancy in estimates between longitudinal studies with repeated assessments (the gold-standard), yielding approximately constant rates of depression, versus cross-sectional studies which often find increasing rates closer in time to the interview. Repeated assessments of current status (or recent history) are more reliable than reconstruction of a person's psychiatric history based on a single interview. In this paper, we demonstrate a method of estimating a time-varying measurement error distribution in the age of onset of an initial depressive episode, as diagnosed by the CIDI, based on an assumption regarding age-specific incidence rates. High-dimensional non-parametric estimation is achieved by the EM-algorithm with smoothing. The method is applied to data from a Norwegian mental health survey in 2000. The measurement error distribution changes dramatically from 1980 to 2000, with increasing variance and greater bias further away in time from the interview. Some influence of the measurement error on already published results is found.     

Identifying radon-prone building typologies by marginal modelling

Radon is a naturally occurring decay product of uranium known to be the main contributor to natural background radiation exposure. It has been established that the health risk related to radon exposure is lung cancer. In fact, radon is considered to be a major leading cause of lung cancer, second only to smoking. In this paper, we identified building typologies that affect the probability of detecting indoor radon concentration above reference values, using the data collected within two monitoring campaigns recently conducted in Northern Italy. This information is fundamental both in prevention, i.e. when the construction of a new building is planned and in mitigation, i.e. when a high concentration detected inside buildings has to be reduced. A spatial regression approach for binary data was adopted for this goal where some relevant covariates on the soil were retrieved by linking external spatial databases.     

On optimising the estimation of high quantiles of a probability distribution

One of the major aims of one-dimensional extreme-value theory is to estimate quantiles outside the sample or at the boundary of the sample. The underlying idea of any method to do this is to estimate a quantile well inside the sample but near the boundary and then to shift it somehow to the right place. The choice of this “anchor quantile” plays a major role in the accuracy of the method. We present a bootstrap method to achieve the optimal choice of sample fraction in the estimation of either high quantile or endpoint estimation which extends earlier results by Hall and Weissman (1997) in the case of high quantile estimation. We give detailed results for the estimators used by Dekkers et al. (1989). An alternative way of attacking problems like this one is given in a paper by Drees and Kaufmann (1998).     

Percentile Related Bounds and Estimator for the Mean of the Negative Binomial Distribution

Upper and lower bounds are obtained for the mean of the negative binomial distribution. These bounds are simple functions of a percentile determined by the shape parameter. The result is then used to obtain a robust estimate of the mean when the shape parameter is known.