On the Bayesian analysis of categorical data: the problem of nonresponse

It is demonstrated how a suitably chosen prior for the frequency parameters can streamline the Bayesian analysis of categorical data with missing entries due to nonresponse or other causes. The two cases where the data follow the Multinomial or the Hypergeometric model are treated separately. In the first case it is adequate to restrict the prior (for the cell probabilities) to the class of Dirichlet distributions. In the case of the Hypergeometric model it is convenient to select a prior from the class of Dirichlet-Multinomial (DM) distributions. The DM distributions are studied in some details.     

Work-related factors contributing to chronic disability in low back pain

Low back pain is a costly and incapacitating musculoskeletal disorder. Prospective studies documenting the capacity of work-related factors to predict chronicity are few in number, the methodology used is very diversified, and the results obtained diverge. The aim of the present study is to investigate the capacity of work-related objective (non-psychosocial) and psychosocial factors to predict chronic disability related to low back pain. A longitudinal prospective study with two measurement times was carried out. The sample (N = 258) consisted of workers with subacute low back pain who were on sick leave and receiving compensation from the CSST (Quebec Workers' Compensation Board). Of all the work-related variables measured, perceived stress and fears and beliefs about work were associated with return to work status at the six-month follow-up. The results obtained show the importance of considering fears and beliefs about work when identifying people in the subacute phase of low back pain who are at risk of developing chronic disability.     

Unit Roots: Bayesian Significance Test

The unit root problem plays a central role in empirical applications in the time series econometric literature. However, significance tests developed under the frequentist tradition present various conceptual problems that jeopardize the power of these tests, especially for small samples. Bayesian alternatives, although having interesting interpretations and being precisely defined, experience problems due to the fact that that the hypothesis of interest in this case is sharp or precise. The Bayesian significance test used in this article, for the unit root hypothesis, is based solely on the posterior density function, without the need of imposing positive probabilities to sets of zero Lebesgue measure. Furthermore, it is conducted under strict observance of the likelihood principle. It was designed mainly for testing sharp null hypotheses and it is called FBST for Full Bayesian Significance Test.     

Nonnested Testing for Competing Autoregressive Dynamic Models Estimated by Instrumental Variables

In this work we investigate nonnested tests for two competing univariate dynamic linear models with autoregressive disturbances, where the motivation for instrumental variable estimation is mainly due to the recognized presence of current endogenous variables in the regression function, either in one or both models. As the previous transformation of both models yields regression functions which are nonlinear in the parameters, the attractive Gauss-Newton regression (GNR) approach, firstly advocated by Davidson and Mackinnon (1981 Davidson , R. , Mackinnon , J. G. ( 1981 ). Several tests for model specification in the presence of alternative hypotheses . Econometrica 49 : 781 – 93 .[Crossref], [Web of Science ®] , [Google Scholar]), will be used to obtain the results.     

Waiting time to exhaust lottery numbers

Questions related to lotteries are usually of interest to the public since people think there is a magic formula which will help them to win lottery draws. This note shows how to compute the expected waiting time to observe specific numbers in a sequence of lottery draws and show that surprising facts are expected to occur.     

On quantile residuals in beta regression

Beta regression is often used to model the relationship between a dependent variable that assumes values on the open interval (0, 1) and a set of predictor variables. An important challenge in beta regression is to find residuals whose distribution is well approximated by the standard normal distribution. Two previous works compared residuals in beta regression, but the authors did not include the quantile residual. Using Monte Carlo simulation techniques, this article studies the behavior of certain residuals in beta regression in several scenarios. Overall, the results suggest that the distribution of the quantile residual is better approximated by the standard normal distribution than that of the other residuals in most scenarios. Three applications illustrate the effectiveness of the quantile residual.     

Changes in preschool children’s social engagement positively predict changes in social competence: A three‐year longitudinal study of portuguese children

To test the hypothesis that social engagement is a foundational aspect of other peer social competence indicators during early childhood, 160 Portuguese preschool children (“3‐year‐olds”) were observed at least in two different school years, using a battery of validated social competence assessments based on direct observations and child interviews. Multilevel growth models tested whether social engagement predicted initial values and linear changes in the other social competence indicators. Results were consistent with the hypothesis, insofar as both initial values and changes in social engagement significantly predicted initial values and changes in other social competence indicators. Additionally, the number of children's reciprocated friendships was also predicted by social engagement. These results are discussed from the perspectives of conceptual frameworks that consider individual differences in social competence during early childhood as a consequence of attachment histories and/or emotional competence.     

The ‘good mother’ struggles: Obstacles to the attainment of motherhood ideals among adult women formerly placed in residential care

We analysed narratives of motherhood produced by 13 women who were involved with the welfare system or the justice system during adolescence. The original contribution of our study was its focus on mothers who were turning age 30, so they were not in that period of generalized instability that characterizes the transition from care and into adulthood. This qualitative study was part of a larger study on French‐Canadian adolescents with a history of residential care. Semi‐directed interviews were conducted with 13 women, more than 15 years after their admission to residential care. Our data highlights that motherhood can contribute to the vulnerability of women who were involved with the welfare or the justice system as adolescents. Our results suggest that in order to shed a perceived deviant label and to compensate for the adverse events they experienced, they pursue internalized ideals of “good motherhood” that translate into restrictions and strain. Furthermore, they tend to refrain from allowing people into their lives and asking for help for fear of being judged. Yet, as their children are getting older and exhibiting problem behaviors of their own, the questioning of their parental practices and skills only becomes more intense.     

Influence diagnostics for Student-t censored linear regression models

In this paper, we extend the censored linear regression model with normal errors to Student-t errors. A simple EM-type algorithm for iteratively computing maximum-likelihood estimates of the parameters is presented. To examine the performance of the proposed model, case-deletion and local influence techniques are developed to show its robust aspect against outlying and influential observations. This is done by the analysis of the sensitivity of the EM estimates under some usual perturbation schemes in the model or data and by inspecting some proposed diagnostic graphics. The efficacy of the method is verified through the analysis of simulated data sets and modelling a real data set first analysed under normal errors. The proposed algorithm and methods are implemented in the R package CensRegMod.