Alternative beta estimation for the market model using partially adaptive techniques

The leptokurtosls of many security market return distributions can contaminate ordinary least squares estimates of the β coefficient of the market model. Partially adaptive estimation techniques accommodate the possibility of fat tailed distributions. this methodology limits the influence of extremely large residuals and yields estimates which are both statistically and practically different from ordinary least squares.     

The probability integral for a bivariate generalization of the non-central t

An expression for the probability integral of a bivariate generalization of the non-central t distribution is derived. This expression is then used to construct tables for various combinations of parameter values     

Trends in Gambling Studies Research: Quantifying, Categorizing, and Describing Citations

As opportunities to gamble have increased during the 20th century, so has gambling research. This study used new strategies, methods, and technology to examine citation trends and the growth of knowledge in the field of gambling studies. The sample included 2,246 citations that were published between 1903 and 2003. By using multiple keywords to classify each citation into distinct topic areas, this study yielded a more comprehensive analysis than was previously available. The results reveal that gambling-related research has grown at an exponential rate. The most prevalent topics explored within gambling studies citations have been pathology, risk-taking, decision-making and addiction. Between 1999 and 2003, studies addressing epidemiology, drug abuse, comorbidity and neuroscience have become increasingly prevalent. Based on these trends and their implications, this paper provides several recommendations for both future areas of inquiry within the field of gambling studies and better classification techniques for citations within all fields of psychology.     

The Proxy Effect: Gender and Gambling Problem Trajectories of Iowa Gambling Treatment Program Participants

Recent research has found that men and women who end up in gambling treatment tend to follow different trajectories to that endpoint: women generally begin gambling later in life, but progress to problems and seek treatment more quickly. With women’s prevalence rates of gambling and disordered gambling increasing, it has become important to identify the causes and consequences of these trajectory differences. The current study used a sample of 2,256 gamblers enrolled in the Iowa Gambling Treatment Program to examine the relationship of gender and other demographic, economic and health-related (i.e., psychosocial) factors to empirically-identified gambling problem trajectories. The results indicated that gender made a statistically significant contribution to the prediction of trajectory, but increased predictive accuracy by only 1–2% beyond a model with psychosocial predictors. Gender’s contribution was limited to its relationship to age of initiation; men and women’s problem progression did not differ meaningfully once age of gambling initiation was taken into account. Gender is a unique contributor to the development of gambling problems among treatment seekers, but it is only one small part of the myriad psychosocial characteristics that influence gambling problem development.

On population‐based measures of agreement for binary classifications

The authors describe a model‐based kappa statistic for binary classifications which is interpretable in the same manner as Scott's pi and Cohen's kappa, yet does not suffer from the same flaws. They compare this statistic with the data‐driven and population‐based forms of Scott's pi in a population‐based setting where many raters and subjects are involved, and inference regarding the underlying diagnostic procedure is of interest. The authors show that Cohen's kappa and Scott's pi seriously underestimate agreement between experts classifying subjects for a rare disease; in contrast, the new statistic is robust to changes in prevalence. The performance of the three statistics is illustrated with simulations and prostate cancer data.     

On confidence regions for the mean of a multivariate time series

We consider the problem of setting up a confidence region for the mean of amultivariate timeseries ont he basis of a part-realisation of that series.A procedure for setting up a confidence interval for the mean of a univariate time series Is implicitin Jones(1976).We present an analogous procedure for setting up a confidence region for the mean of a multivariatet ime series.This procedure is base donastatistic which is an analogue of Hotelling'sT'.Our results are applied to a comparison of climate means obtained from experiments with a General Circulation Model of the earth's atmosphere.     

Health care trends, Part 2. The new health care team. Panel discussion

In Part 2 of this third annual panel discussion, six experts talk about the growing diversity of health care providers and what it means for consumers and physicians. Americans are getting their wellness and health care services from a wider variety of non-physician practitioners than ever before. The number of allied health and alternative providers with direct patient access is likely to continue growing. This trend is being driven by consumer demand, by the lobbying efforts of non-physician providers, and by federal, state, and private payers who see the potential for reduced health care spending, greater consumer satisfaction, and better outcomes. In practice, this means physicians and non-physician providers, some of whom may not be sanctioned by the medical establishment, are obligated to collaborate as a team. Members of this new provider team will have to communicate effectively (with each other, with consumers, and with payers) and make evidence-based clinical decisions. Physicians may have to share decision-making with other members of this new health care team.     

College student binge drinking and the "prevention paradox": implications for prevention and harm reduction

Considerable attention has been paid to heavy episodic or "binge" drinking among college youth in the United States. Despite widespread use, the binge measure is perceived by some as a low intervention threshold. We use data from the Harvard School of Public Health College Alcohol Study (n = 49,163) to describe patterns of consumption and harms along a continuum including the binge measure to demonstrate the validity of the binge threshold and prevention paradox in college. While the heaviest drinkers are at greatest risk for harm, they are relatively few and generate proportionately small amounts of all drinking-harms. The risk of harms is not zero among lower level drinkers in college. Because they are numerous, they account for the majority of harms. This paradoxical pattern suggests we moderate consumption among the majority using environmental approaches, the efficacy of which are described using case study data from a national prevention demonstration. Implications for prevention policy, programming, and media advocacy are discussed.