On correlation analysis of many‐to‐many observations: an alternative to Pearson's correlation coefficient and its application to an ecotoxicological study

Correlation studies are an important hypothesis‐generating and testing tool, and have a wide range of applications in many scientific fields. In ecological studies in particular, multiple environmental variables are often measured in an attempt to determine relationships between chemical, physical and biological factors. For example, one may wish to know whether and how soil properties correlate with plant physiology. Although correlation coefficients are widely used, their properties and limitations are often imperfectly understood. This is especially the case when one is interested in correlations between, say, trace element content in sediments and in marine organisms, where no one‐to‐one correspondence exists. We show that evaluating Pearson's correlation coefficient for either site‐specific means or composite samples results in biased estimates, and we propose an alternative estimator. We use simulation studies to demonstrate that our estimator generally has a much smaller bias and mean squared error. We further illustrate its use in a case study of the correlation between trace element content in sediments and in mussels in Lyttelton Harbour, New Zealand.     

Ergonomics of bridge employment

In many countries of the world, retirement is mandatory at the age at which persons who hold certain jobs or offices are required by employment law to leave their employment, or retire (60 to 65 years). Typically, this is justified by the argument that certain occupations are either too dangerous or require high levels of physical skills and mental work. Every worker has to leave the workforce at that age. However, starting from the last two decades of the last century, it is observed that retirees live more years in retirement than ever before. This relatively long retirement as well as retirees' body fitness made many of them engage in new jobs which are either similar to their career jobs, or completely different from them. In this new type of employment which is called "bridge employment', the retired worker may spend more than ten years. But, to what extent these new jobs are fitted to the aged worker? Considering that experiencing any type of event increases the risk of worse health outcomes over time, bridge employment should be ergonomically designed if it is to fit the aged worker characteristics (physical, mental and affective).     

Modified ridge-type for the Poisson regression model: simulation and application

The Poisson regression model (PRM) is employed in modelling the relationship between a count variable (y) and one or more explanatory variables. The parameters of PRM are popularly estimated using the Poisson maximum likelihood estimator (PMLE). There is a tendency that the explanatory variables grow together, which results in the problem of multicollinearity. The variance of the PMLE becomes inflated in the presence of multicollinearity. The Poisson ridge regression (PRRE) and Liu estimator (PLE) have been suggested as an alternative to the PMLE. However, in this study, we propose a new estimator to estimate the regression coefficients for the PRM when multicollinearity is a challenge. We perform a simulation study under different specifications to assess the performance of the new estimator and the existing ones. The performance was evaluated using the scalar mean square error criterion and the mean squared error prediction error. The aircraft damage data was adopted for the application study and the estimators’ performance judged by the SMSE and the mean squared prediction error. The theoretical comparison shows that the proposed estimator outperforms other estimators. This is further supported by the simulation study and the application result.KEYWORDS: Poisson regression model, Poisson maximum likelihood estimator, multicollinearity, Poisson ridge regression, Liu estimator, simulation     

A flexible fixed-sequence testing method for hierarchically ordered correlated multiple endpoints in clinical trials

Statistical approaches for addressing multiplicity in clinical trials range from the very conservative (the Bonferroni method) to the least conservative the fixed sequence approach. Recently, several authors proposed methods that combine merits of the two extreme approaches. Wiens [2003. A fixed sequence Bonferroni procedure for testing multiple endpoints. Pharmaceutical Statist. 2003, 2, 211–215], for example, considered an extension of the Bonferroni approach where the type I error rate (α)$(\alpha )$ is allocated among the endpoints, however, testing proceeds in a pre-determined order allowing the type I error rate to be saved for later use as long as the null hypotheses are rejected. This leads to a higher power of the test in testing later null hypotheses. In this paper, we consider an extension of Wiens’ approach by taking into account correlations among endpoints for achieving higher flexibility in testing. We show strong control of the family-wise type I error rate for this extension and provide critical values and significance levels for testing up to three endpoints with equal correlations and show how to calculate them for other correlation structures. We also present results of a simulation experiment for comparing the power of the proposed method with those of Wiens’ and others. The results of this experiment show that the magnitude of the gain in power of the proposed method depends on the prospective ordering of testing of the endpoints, the magnitude of the treatment effects of the endpoints and the magnitude of correlation between endpoints. Finally, we consider applications of the proposed method for clinical trials with multiple time points and multiple doses, where correlations among endpoints frequently arise.     

Packing trees in communication networks

Given an undirected edge-capacitated graph and given (possibly) different subsets of vertices, we consider the problem of selecting a maximum (weighted) set of Steiner trees, each tree spanning a subset of vertices, without violating the capacity constraints. This problem is motivated by applications in multicast communication networks. We give an integer linear programming (ILP) formulation for the problem, and observe that its linear programming (LP) relaxation is a fractional packing problem with exponentially many variables and a block (sub-)problem that cannot be solved in polynomial time. To this end, we take an r-approximate block solver (a weak block solver) to develop a (1−ε)/r-approximation algorithm for the LP relaxation. The algorithm has a polynomial coordination complexity for any ε∈(0,1). To the best of our knowledge, this is the first approximation result for fractional packing problems with only weak block solvers (with arbitrarily large approximation ratio) and a coordination complexity that is polynomial in the input size. This leads also to an approximation algorithm for the underlying tree packing problem. Finally, we extend our results to an important multicast routing and wavelength assignment problem in optical networks, where each Steiner tree is to be assigned one of a limited set of given wavelengths, so that trees crossing the same fiber are assigned different wavelengths. A preliminary version of this paper appeared in the Proceedings of the 1st Workshop on Internet and Network Economics (WINE 2005), LNCS, vol. 3828, pp. 688–697. Research supported by a MITACS grant for all the authors, an NSERC post doctoral fellowship for the first author, the NSERC Discovery Grant #5-48923 for the second and fourth author, NSERC Discovery Grant #15296 for the third author, the Canada Research Chair Program for the second author, and an NSERC industrial and development fellowship for the fourth author.     

A note on the equivariant estimation of an exponential scale using progressively censored data

We consider the problem of estimating the scale parameter θ$\theta$ of the shifted exponential distribution with unknown location based on a type II progressively censored sample. Under a large class of bowl-shaped loss functions, a smooth estimator, that dominates the minimum risk equivariant estimator of θ$\theta$, is proposed. A numerical study is performed and shows that the improved estimator yields significant risk reduction over the MRE.     

Time Preferences and Job Search: Evidence from France

Abstract. Increasing impatience reduces search efforts of unemployed job seekers and therefore decreases the exit rate from unemployment. Also, impatience reduces reservation wage and increases the exit rate. To determine the overall effect of impatience on the exit rate from unemployment, we distinguish between exponential and hyperbolic time preferences. Search effort dominates the reservation wage and decreases the exit rate from unemployment if individuals have hyperbolic, rather than exponential, preferences. Using the French sample of the European Household Panel Survey, we found that search effort has a strong effect on the duration of unemployment, whereas the reservation wage is not significant. This result shows that the job seekers have hyperbolic preferences. Hyperbolic preferences affect problems associated with job search and policies aimed at reducing unemployment.     

Redistributed Manufacturing and the Impact of Big Data: A Consumer Goods Perspective

Abstract

Digitalization and the growth of big data promise greater customization as well as change in how manufacturing is distributed. Yet, challenges arise in applying these new approaches in consumer goods industries that often emphasize mass production and extended supply chains. We build a conceptual framework to explore whether big data combined with new manufacturing technologies can facilitate redistributed manufacturing (RDM). Through analysis of 24 consumer goods industry cases using primary and secondary data, we investigated evolving manufacturing configurations, their underlying drivers, the role of big data applications, and their impact on the redistribution of manufacturing. We find some applications of RDM concepts, although in other cases existing manufacturing configurations are leveraged for high volume consumer goods products through big data analytics and market segmentation. The analysis indicates that the framework put forward in the paper has broader value in organizing thinking about emerging interrelationships between big data and manufacturing.     

Value-at-risk estimation by LS-SVR and FS-LS-SVR based on GAS model

ABSTRACT

Conditional risk measuring plays an important role in financial regulation and depends on volatility estimation. A new class of parameter models called Generalized Autoregressive Score (GAS) model has been successfully applied for different error's densities and for different problems of time series prediction in particular for volatility modeling and VaR estimation. To improve the estimating accuracy of the GAS model, this study proposed a semi-parametric method, LS-SVR and FS-LS-SVR applied to the GAS model to estimate the conditional VaR. In particular, we fit the GAS(1,1) model to the return series using three different distributions. Then, LS-SVR and FS-LS-SVR approximate the GAS(1,1) model. An empirical research was performed to illustrate the effectiveness of the proposed method. More precisely, the experimental results from four stock indexes returns suggest that using hybrid models, GAS-LS-SVR and GAS-FS-LS-SVR provides improved performances in the VaR estimation.     

Perinatal and social factors predicting caesarean birth in a 2004 Australian birth cohort

Background

The proportion of babies born by caesarean section in Australia has almost doubled over the last 25 years. Factors known to contribute to caesarean such as higher maternal age, mothers being overweight or obese, or having had a previous caesarean do not completely account for the increased rate and it is clear that other influences exist.