Sample sizes for estimation in clinical research

A sample size justification should be given for all clinical investigations. However, sometimes the objective of a trial is to estimate an effect with a view to planning a later definitive study. This paper describes the calculations for designing studies where one wishes to adopt an estimation approach through using confidence intervals around the overall response. Calculations are given for data anticipated to take a Normal form. Copyright © 2004 John Wiley & Sons, Ltd.     

BAYESIAN MODEL SEARCH AND MULTILEVEL INFERENCE FOR SNP ASSOCIATION STUDIES

Technological advances in genotyping have given rise to hypothesis-based association studies of increasing scope. As a result, the scientific hypotheses addressed by these studies have become more complex and more difficult to address using existing analytic methodologies. Obstacles to analysis include inference in the face of multiple comparisons, complications arising from correlations among the SNPs (single nucleotide polymorphisms), choice of their genetic parametrization and missing data. In this paper we present an efficient Bayesian model search strategy that searches over the space of genetic markers and their genetic parametrization. The resulting method for Multilevel Inference of SNP Associations, MISA, allows computation of multilevel posterior probabilities and Bayes factors at the global, gene and SNP level, with the prior distribution on SNP inclusion in the model providing an intrinsic multiplicity correction. We use simulated data sets to characterize MISA's statistical power, and show that MISA has higher power to detect association than standard procedures. Using data from the North Carolina Ovarian Cancer Study (NCOCS), MISA identifies variants that were not identified by standard methods and have been externally "validated" in independent studies. We examine sensitivity of the NCOCS results to prior choice and method for imputing missing data. MISA is available in an R package on CRAN.     

Tail exponent estimation via broadband log density-quantile regression

Heavy tail probability distributions are important in many scientific disciplines such as hydrology, geology, and physics and therefore feature heavily in statistical practice. Rather than specifying a family of heavy-tailed distributions for a given application, it is more common to use a nonparametric approach, where the distributions are classified according to the tail behavior. Through the use of the logarithm of Parzen's density-quantile function, this work proposes a consistent, flexible estimator of the tail exponent. The approach we develop is based on a Fourier series estimator and allows for separate estimates of the left and right tail exponents. The theoretical properties for the tail exponent estimator are determined, and we also provide some results of independent interest that may be used to establish weak convergence of stochastic processes. We assess the practical performance of the method by exploring its finite sample properties in simulation studies. The overall performance is competitive with classical tail index estimators, and, in contrast, with these our method obtains somewhat better results in the case of lighter heavy-tailed distributions.     

A Demographic Model of Measles Epidemics

Liverpool, U.K., 1863--1900, has been used as a model to explore the interaction between measles epidemics and the population dynamics in an overcrowded community with inadequate nutrition using a non-linear model which allows the estimation of certain underlying demographic parameters. The results are consistent with a system that is driven by an oscillation in the transmission parameter that is compounded of an oscillation in autumn temperatures (at the resonant frequency of the system, 2.4 years) and, secondarily, by an oscillation in wheat prices (wavelength = 5.3 years, twice that of the epidemics).     

Rehabilitation outlooks for rural Louisiana: educational developments,economic trends,and global perspectives

The objective of this article is to examine current medical, economic, and social trends affecting the provision of rehabilitation services for rural citizens with disabilities. While the population of interest is citizens of Louisiana, the concepts are applicable across all geographic boundaries. The article is a review of clinical practice, job placement alternatives, economic trends, and assessment of process applications. It is concluded numerous steps may be taken to enhance the availability and quality of services provided for rural citizens with disabilities: greater statistical inquiry into rural disability trends, increased incorporation of the Internet into all aspects of rural economic and educational developments, further development of distance learning, promotion of sensitivities towards rural cultures, and continued recruitment of rural allied and vocational rehabilitation professionals.     

Demographic and situational factors affecting injury, resistance, completion, and charges brought in sexual assault cases: what is best for arrest?

This study examines demographic and situational factors in an effort to predict whether or not a complainant was injured, used resistance, experienced a completed assault, and whether charges were brought against the offender. If the accused had consumed alcohol or drugs, he was almost seven times more likely to be arrested. The complainant was six times more likely to report rape completion if she had consumed alcohol or drugs and if the complainant fell unconscious at any time during the attack she was significantly less likely to use a resistance strategy. The complainant's use of a compliance strategy at any time during the assault positively predicted not using a physical resistance strategy and sexual assault completion. The reporting of injury positively predicted use a physical resistance strategy and sexual assault completion. If the assault was completed, it was less likely that charges were pressed. Implications of these findings are discussed, and directions for future research are offered.     

Vital connections

Scientists are currently exploring the structure and behavior of complex biological systems, which consist of networks of interacting entities. A recent paper in Proceedings of the Royal Society of London Series B Biological Sciences describes the distinctive characteristics of aging-related proteins in the yeast protein-protein interaction network. In this Perspective, I discuss the implications of these findings for longevity research.     

Contiguity of Probability Measures

The notion of contiguity of probability measures is a very useful one, providing a generally applicable method of calculating the asymptotic power of a sequence of tests and thus a means of comparing competing tests. This paper attempts to give an account of the basic results of contiguity theory which is self-contained and accessible to statisticians to whom the theory is of use. In addition, the relationship between contiguity and mutual contiguity is explored.     

THE THERAPEUTIC ALLIANCE IN HOME‐BASED FAMILY THERAPY: IS IT PREDICTIVE OF OUTCOME?

This study examined the association between the therapeutic alliance in family therapy and changes in symptom distress, interpersonal relationships, and family coping. The participants (N = 81) were members of low socioeconomic status families referred to a university clinic for in-home family therapy. Participants completed the Outcome Questionnaire, Family Crisis Oriented Personal Evaluation, and the Family Therapy Alliance questionnaires. Regression analyses revealed that the therapeutic alliance explained 19% of the variance in symptom distress changes for mother, 55% for fathers, and 39% for adolescents. The implications of these findings for practicing and researching family therapy are presented.