Properties of generalized Levinson–Durbin–Whittle sequences

For a discrete time, second-order stationary process the Levinson–Durbin recursion is used to determine best fitting one-step-ahead linear autoregressive predictors of successively increasing order, best in the sense of minimizing the mean square error. Whittle [1963. On the fitting of multivariate autoregressions, and the approximate canonical factorization of a spectral density matrix. Biometrika 50, 129–134] generalized the recursion to the case of vector autoregressive processes. The recursion defines what is termed a Levinson–Durbin–Whittle sequence, and a generalized Levinson–Durbin–Whittle sequence is also defined. Generalized Levinson–Durbin–Whittle sequences are shown to satisfy summation formulas which generalize summation formulas satisfied by binomial coefficients. The formulas can be expressed in terms of the partial correlation sequence, and they assume simple forms for time-reversible processes. The results extend comparable formulas obtained in Shaman [2007. Generalized Levinson–Durbin sequences, binomial coefficients and autoregressive estimation. Working paper] for univariate processes.     

On the Order of Data Reductions by Ancillarity and by Sufficiency

In the context of frequentist inference there are strong arguments in favour of data reduction by both (a) conditioning on the most appropriate ancillary statistic and (b) restricting attention to a minimal sufficient statistic. However, significantly for the study of the foundations of frequentist inference, there are some examples in which the order of application of these data reductions has an important bearing on the statistical inference of interest. This paper presents a new simple example of this kind.     

Incorporation of historical controls using semiparametric mixed models

The analysis of animal carcinogenicity data is complicated by various statistical issues. A topic of recent debate is how to control for the effect of the animal's body weight on the outcome of interest, the onset of tumours. We propose a method which incorporates historical information from the control animals in previously conducted experiments. We allow non-linearity in the effects of body weight by modelling the relationship nonparametrically through a penalized spline. A simple extension of the penalized spline model allows the relationship between weight and the onset of tumour to vary from one experiment to another.     

Approximate and exact distributions of rank tests for balanced incomplete block designs

Judges rank k out of t objects according to m replic ations of abasic balanced incomplete block design with bblocks. In Alvo and Cabilio(1991),it is shown that the Durbin test, which is the usual test in this situation, can be written in terms of Spearman correlations between the blocks, and using a Kendall correlation, they generated a new statistic for this situation.This Kendall tau based statistic has a richer support than the Durbin statistic, and is at least as efficient.In the present paper,exact and simulation based tables are generated for both statistics, and various approximations to these null distributions are considered and compared.     

Impact of Canadian Postsecondary Education on Occupational Prestige of Highly Educated Immigrants

Cet article utilise les données provenant de l'Enquête longitudinale auprès des immigrants du Canada (ELIC) couvrant la période 2000‐2004 afin d'évaluer l'emploi à durée déterminée et la réussite professionnelle des immigrants récents qui, bien qu'ayant obtenu un diplôme universitaire dans leur pays d'origine, ont choisi de s'inscrire dans un établissement d'enseignement postsecondaire canadien. La principale conclusion de l'article est que la réussite professionnelle des immigrants très instruits est affectée par le choix de l'enseignement post‐secondaire au Canada, toutes catégories socio‐démographiques et conditions d'avant ou après migration confondues. Quatre années après leur arrivée au Canada, les immigrants occupent des emplois nettement moins prestigieux que ceux qu'ils avaient avant la migration. Les immigrants qui ont poursuivi des études universitaires au Canada atteignent des meilleurs résultats professionnels que les non‐participants ou ceux qui ont choisi un collège communautaire. Néanmoins, la majorité des immigrants très instruits n'ont pas réussi à retrouver leur profession. This paper uses data from the Longitudinal Survey of Immigrants to Canada covering the period 2000 to 2004 to assess short‐term employment and occupational attainment of recent immigrants who, despite having completed a university degree in their countries of origin, chose to obtain additional credentials at a Canadian postsecondary institution. The main finding of this paper is that occupational attainment of highly educated immigrants is affected by choice of postsecondary education in Canada regardless of differences in sociodemographic, premigration characteristics, and postmigration conditions. Four years after entry, immigrants worked in jobs with significantly lower occupational prestige than those held prior to migration. Immigrants who pursued a university education in Canada attained highest occupational outcomes when compared to nonparticipants and those who chose a community college pathway. Nevertheless, the majority of highly educated immigrants failed to gain entry to the professions.     

Supplemental Security Income recipients affected by Hurricanes Katrina and Rita: an analysis of two years of administrative data

Approximately 350,000 Supplemental Security Income (SSI) recipients—elderly and disabled individuals with low incomes and assets—lived in the areas directly affected by Hurricanes Katrina and Rita in August 2005. We show that recipients from affected areas were more likely to leave the program, have more volatile participation patterns, and leave the area in the 2 years following the hurricanes than were recipients from unaffected areas. Among recipients from more severely affected areas relative to those from unaffected states, the odds of dying were 40% greater and the odds of leaving SSI for other reasons were 23% greater. Additionally, 31% of recipients from more severely affected areas had experienced a non-payment month, with 46% subsequently returning to the rolls (compared with 23% and 41% of recipients from unaffected states). Nearly 60% of SSI recipients from more severely affected areas lived in a different county or parish 2 years after the hurricanes, compared with about 12% from unaffected areas. In all, our findings demonstrate that natural disasters such as Hurricanes Katrina and Rita can have large and persistent impacts on SSI recipients, including effects on program status, mortality, and geographic location.     

A Study of Suicide Risk Using a Cox Cure Model via a Retrospective Sampling and Multiple Imputation

The incidence of suicide is an example of rare event. A Cox cure model is adopted to examine the suicide risk of a cohort study of a sample of 65,000 Personal Emergency Link users over a 10-year observation period. Our objective is to investigate the effect of personal covariates on the failure time to suicide as well as the long-term survival from suicide. Based on the Cox cure model, a new and efficient estimation approach using retrospective sampling and multiple imputation was used. Compared with the standard Cox proportional hazards model, the Cox cure model provides a new perspective on analyzing the suicide data.     

Marketing Strategies and Market Prospects for Environmentally-Friendly Consumer Products1

Recent evidence suggests that the extent of consumer adoption of ‘green’ products is much less than would be indicated by the enthusiastic opinion poll evidence concerning public attitudes towards environmentally-friendly consumption. This paper reports on an empirical analysis of firms' marketing strategies and their influence on consumer demand for green products. In twenty 2–3 hour interviews with senior managers, four representative groups of markets were analysed household detergents, paper (recycled), petrol (unleaded) and automobile technology (focusing on catalytic converters). According to managers, firms' marketing strategies influenced consumer demand by making green technologies available in the fwst instance. However, barriers to supplying green products that show panty with, or better performance than, conventional technologies constrain pricing and communication efforts Managers stressed that, in the absence of clarity of green products' environmental benefits, product performance and other attributes, not green benefits, remain the main determinants of product preference and choice. Promotions focused much more on consumers than distribution channels, yet channel acceptance and support of green innovations are paramount in facilitating sales. Firms see the costs of generating and promoting desirable green technologies as barriers to diffusion in the immediate future. Legislation and/or economic incentives may help, but manufacturers are not optimistic that future green consumption rates will accelerate. The results also highlight several propositions concerning the discrepancy between consumer environmental concerns and purchasing actions which warrant further testing: there is mis-specification of green products in relation to consumers'needs; there are barriers to perceptions of green products' environmental impact and consumers' free ride due to individual self-interest.