BAYESIAN SUBSET SELECTION AND MODEL AVERAGING USING A CENTRED AND DISPERSED PRIOR FOR THE ERROR VARIANCE

This article proposes a new data‐based prior distribution for the error variance in a Gaussian linear regression model, when the model is used for Bayesian variable selection and model averaging. For a given subset of variables in the model, this prior has a mode that is an unbiased estimator of the error variance but is suitably dispersed to make it uninformative relative to the marginal likelihood. The advantage of this empirical Bayes prior for the error variance is that it is centred and dispersed sensibly and avoids the arbitrary specification of hyperparameters. The performance of the new prior is compared to that of a prior proposed previously in the literature using several simulated examples and two loss functions. For each example our paper also reports results for the model that orthogonalizes the predictor variables before performing subset selection. A real example is also investigated. The empirical results suggest that for both the simulated and real data, the performance of the estimators based on the prior proposed in our article compares favourably with that of a prior used previously in the literature.     

Adaptation of the jackknifed ridge methods to the linear mixed models

The purpose of this article is to obtain the jackknifed ridge predictors in the linear mixed models and to examine the superiorities, the linear combinations of the jackknifed ridge predictors over the ridge, principal components regression, r?k class and Henderson's predictors in terms of bias, covariance matrix and mean square error criteria. Numerical analyses are considered to illustrate the findings and a simulation study is conducted to see the performance of the jackknifed ridge predictors.     

Patterns and severity of menopausal symptoms among Jordanian women

We examined 359 women aged 45–65 years who visited Jordan University Hospital between February and November 2014. The menopausal symptoms were assessed using a validated Arabic version of the menopause rating scale. The mean age at menopause was 49.4 years. Women aged 50–55 years more frequently exhibited hot flushes and vaginal dryness. Although premenopausal women were 1.5 times more likely to experience irritability, perimenopausal women were more likely to experience hot flushes, physical and mental irritability, sexual problems, vaginal dryness, and joint and muscular discomfort. Hence, health care providers should focus on women at all stages of life.     

Trajectories of Gambling During Adolescence

This study aimed at empirically identifying groups of adolescents with distinct longitudinal trajectories of gambling involvement and validating these groups by comparing them with respect to correlates. 903 low SES boys were followed annually from age 11 to 16 years. Three groups were found: an early-onset high-level chronic group, a late-onset high-level group, and a low gambler group. The Chronic group and the Low group consistently differed on teacher-rated inhibition (i.e., anxiety) during childhood and early adolescence. They also differed on concurrent teacher and self ratings of disinhibition (i.e., impulsivity), while the Late Onset group appeared to lie in between these groups. Compared to the Low group, both high groups subsequently had elevated scores on later gambling related problems.     

Equivariant prediction in finite populations

A theory of equivariant prediction is developed for predicting the population total in finite populations. Minimum risk equivariant predictors (MREP) are derived under the location, scale and locationscale superpopulation models. Under the general linear model, it is shown that the best(linear) unbiased predictor (B(L)UP) is an MREP.     

Principal point classification: Applications to differentiating drug and placebo responses in longitudinal studies

Principal points are cluster means for theoretical distributions. A discriminant methodology based on principal points is introduced. The principal point classification method is useful in clinical trials where the goal is to distinguish and differentiate between different treatment effects. Particularly, in psychiatric studies where placebo response rates can be very high, the principal point classification is illustrated to distinguish specific drug responders from non-specific placebo responders.     

Estimation of regression models with equi-correlated responses when some observations on the response variable are missing

The present article deals with the problem of estimation of parameters in a linear regression model when some data on response variable is missing and the responses are equi-correlated. The ordinary least squares and optimal homogeneous predictors are employed to find the imputed values of missing observations. Their efficiency properties are analyzed using the small disturbances asymptotic theory. The estimation of regression coefficients using these imputed values is also considered and a comparison of estimators is presented.     

PREDICTION OF THE FINITE POPULATION DISTRIBUTION FUNCTION UNDER GAUSSIAN SUPERPOPULATION MODELS

This article considers optimal prediction of the finite population distribution function under Gaussian superpopulation models, which allows auxiliary prior information to be incorporated into the estimation process. Large sample approximations for the variance of the optimal predictors are derived in some special important cases. A small scale Monte Carlo study illustrates comparisons between the optimal predictor and some others which are proposed in the literature. The conclusion is that the optimal predictor can be considerably more efficient in situations where the normal superpopulation model is adequate.     

Gambling and the Older Chinese in Canada

In Canada, there is a lack of research on gambling among the older adults from ethnic minority groups, especially the older Chinese. In this study, two research questions were used to examine gambling among the older Chinese: (1) What is the pattern of gambling among the older Chinese in Canada? (2) What are the predictors associated with gambling among the older Chinese in Canada? The data for this study were collected as part of a multi-site study on health and well-being of 2272 older Chinese in Canada. Four main questions related to gambling were used in this study. Among the 2257 participants who answered the questions on gambling, 26.6% of them reported that they gambled. Results of the hierarchical logistic regression analysis showed that being male, having lived in Canada longer, having a higher level of social support, having more service barriers, and having a stronger level of Chinese ethnic identity would increase the probability for an older Chinese to participate in gambling. Conversely, having a post-secondary and above level of education and having a higher level of life satisfaction would reduce one’s probability of gambling. Although city of residency was also significant in predicting gambling, further analysis showed that its effect was actually caused by other factors including services barriers, social support, life satisfaction, Chinese ethnic identity, and education.