Accuracy in the long run—Where are we now

Long-term forecasting must be viewed as informative speculation about the future. It should be credited with relatively little scientific authenticity. At the present stage of theory and data, no magic methods can be expected to overcome the problem of satisfactory forecasting. Improvement, however, is certainly not just a question of putting more and more variables and more and more numbers into a computer. Methods which indicate how to cushion against uncertainty and methods which bring a greater awareness of options for the future are essential if we are to gain greater control over events. The hazy images of the long-term future which are generated by scenario and other forms of analysis form the guidelines within which short and especially medium-term choices must be made. But in the end we must recognise the inherent limitations of forecasting and forecasting methods and think of forecasting not so much as a method of prediction but as a contribution to tackling the future in a more integrated sense.     

A monte carlo investigation of a statistic for a bivariate missing data problem

Testing the equal means hypothesis of a bivariate normal distribution with homoscedastic varlates when the data are incomplete is considered. If the correlational parameter, ρ, is known, the well-known theory of the general linear model is easily employed to construct the likelihood ratio test for the two sided alternative. A statistic, T, for the case of ρ unknown is proposed by direct analogy to the likelihood ratio statistic when ρ is known. The null and nonnull distribution of T is investigated by Monte Carlo techniques. It is concluded that T may be compared to the conventional t distribution for testing the null hypothesis and that this procedure results in a substantial increase in power-efficiency over the procedure based on the paired t test which ignores the incomplete data. A Monte Carlo comparison to two statistics proposed by Lin and Stivers (1974) suggests that the test based on T is more conservative than either of their statistics.     

Multilevel particle filters for the non-linear filtering problem in continuous time

Statistics and Computing - In the following article we consider the numerical approximation of the non-linear filter in continuous-time, where the observations and signal follow diffusion...     

Is Adolescent Employment Still a Risk Factor for High School Dropout?

Past cohorts of teenagers who spent long hours in jobs were more likely to drop out of high school than those who worked moderate hours or did not work at all. This article examines the association between employment intensity and dropout among adolescents in the High School Longitudinal Study of 2009 who traversed high school during a time of decreased prevalence of both employment and dropout relative to earlier cohorts. Analyses reveal that a relatively small percentage of teenagers nowadays are characterized as either intensive workers or dropouts (around 11% each). Yet, despite declines in intensive employment and dropout, disadvantaged youth remain overrepresented in both groups, and intensive work is still a risk factor for poor grades and dropout.     

Gay,Lesbian, and Heterosexual Couples About to Begin Couples Therapy: An Online Relationship Assessment of 40,681 Couples

We currently have little idea of precisely who goes for couples therapy. This is a report of the results of a validated online assessment of relationship and individual functioning based on 39,251 heterosexual, 1,022 lesbian, and 438 gay couples about to begin couples therapy. Using validated and reliable questionnaires of relationship and individual functioning, this report presents and compares, for each sexual-orientation, the percentage of couples, pre-therapy, who are coping with a variety of relationship problems. To test for the replicability of results, the sample was divided randomly into two subsamples and statistical tests were performed on each sample. Couples initiating therapy suffer from greater distress and many more co-morbidities than has been presumed in previous literature, and same-sex couples present a particular set of both strengths and challenges compared to heterosexual couples. Gay-male and lesbian couples were very different on trust and monogamy, as were heterosexual and lesbian couples. Based on this epidemiologically sized sample, the challenge to our field may be to create interventions with much larger effect sizes than we currently have.     

Death and the Penguin: modularity,alienation and organising

ABSTRACT

The originality of this paper lies in the ways in which it explores how the depiction of organised crime within Andrey Kurkov’s novel Death and the Penguin can inform our understanding of organisational modularity. This non-orthodox approach might open up new avenues of thought in the study of organisational modularity while further illustrating how novelistic worlds can inform accounts of organisational realities. Two main research questions underlie the paper. How can Andrey Kurkov’s novel further our understanding of the complexity of organisational worlds and realities by focusing our attention on different landscapes of organising? How does Kurkov’s novel help us grasp the concept of modularity by drawing attention to new forms of modular organisation? Drawing from our reading of Kurkov’s novel, we primarily explore organisational modularity through Kurkov’s depiction of organised crime and consider the themes of alienation and isolation in the context of modular organising.     

Physician credentialing. A centralized verification system

The current system for credentialing physicians in the U.S. is staggeringly redundant, prone to error, and expensive. The process for establishing a recent graduate's practice can involve an average of five applications to have privileges at several hospitals and HMOs. A centralized verification system needs to be developed to streamline this process. The amount of information that would have to be stored for all physicians in the country would be immense. However, the technology currently exists to store such information on a much grander scale. Credit unions, banks, and insurance companies utilize such computer systems effectively and with reasonable confidentiality.     

Metropolitan Structure and Neighborhood Attainment: Exploring Intermetropolitan Variation in Racial Residential Segregation

Using data from the 1981, 1991, and 2001 waves of the Panel Study of Income Dynamics and several decennial censuses, we examine how characteristics of metropolitan areas are associated with black and white households’ neighborhood racial composition. Results from hierarchical linear models show that about 20% to 40% of the variation in the percentage of households’ tract population that is non-Hispanic white or non-Hispanic black exists across metropolitan areas. Over time, white households’ exposure to non-Hispanic white neighbors has declined, and their exposure to non-Hispanic black neighbors has increased; the reverse trends are observed for blacks. These trends cannot be attributed to changes in the ecological structure of metropolitan areas. Blacks have fewer white neighbors in large metropolitan areas containing sizable minority populations, and blacks have more white neighbors in metropolitan areas with high government employment. Whites have more black neighbors in metropolitan areas with high levels of government employment and ample new housing; whites have fewer black neighbors in metropolitan areas with a high level of municipal fragmentation. The association between metropolitan-area percentage black and tract percentage black is weaker among whites than among blacks, suggesting that whites are especially motivated to self-segregate in metropolitan areas with large black populations.     

Semiparametric Stochastic Modeling of the Rate Function in Longitudinal Studies

In longitudinal biomedical studies, there is often interest in the rate functions, which describe the functional rates of change of biomarker profiles. This paper proposes a semiparametric approach to model these functions as the realizations of stochastic processes defined by stochastic differential equations. These processes are dependent on the covariates of interest and vary around a specified parametric function. An efficient Markov chain Monte Carlo algorithm is developed for inference. The proposed method is compared with several existing methods in terms of goodness-of-fit and more importantly the ability to forecast future functional data in a simulation study. The proposed methodology is applied to prostate-specific antigen profiles for illustration. Supplementary materials for this paper are available online.