Joint GEEs for multivariate correlated data with incomplete binary outcomes

This study considers a fully-parametric but uncongenial multiple imputation (MI) inference to jointly analyze incomplete binary response variables observed in a correlated data settings. Multiple imputation model is specified as a fully-parametric model based on a multivariate extension of mixed-effects models. Dichotomized imputed datasets are then analyzed using joint GEE models where covariates are associated with the marginal mean of responses with response-specific regression coefficients and a Kronecker product is accommodated for cluster-specific correlation structure for a given response variable and correlation structure between multiple response variables. The validity of the proposed MI-based JGEE (MI-JGEE) approach is assessed through a Monte Carlo simulation study under different scenarios. The simulation results, which are evaluated in terms of bias, mean-squared error, and coverage rate, show that MI-JGEE has promising inferential properties even when the underlying multiple imputation is misspecified. Finally, Adolescent Alcohol Prevention Trial data are used for illustration.     

Marginal models for the association structure of hierarchical binary responses

Clustered binary responses are often found in ecological studies. Data analysis may include modeling the marginal probability response. However, when the association is the main scientific focus, modeling the correlation structure between pairs of responses is the key part of the analysis. Second-order generalized estimating equations (GEE) are established in the literature. Some of them are more efficient in computational terms, especially facing large clusters. Alternating logistic regression (ALR) and orthogonalized residual (ORTH) GEE methods are presented and compared in this paper. Simulation results show a slightly superiority of ALR over ORTH. Marginal probabilities and odds ratios are also estimated and compared in a real ecological study involving a three-level hierarchical clustering. ALR and ORTH models are useful for modeling complex association structure with large cluster sizes.     

Comparison of the effectiveness of forecasts obtained by means of selected probability functions with respect to forecast error distributions

The forecasting of sales in a company is one of the crucial challenges that must be faced. Nowadays, there is a large spectrum of methods that enable making reliable forecasts. However, sometimes the nature of time series excludes many well-known and widely used forecasting methods (e.g., econometric models). Therefore, the authors decided to forecast on the basis of a seasonally adjusted median of selected probability distributions. The obtained forecasts were verified by means of distributions of the Theil U² coefficient and unbiasedness coefficient.     

A general long-term aging model with different underlying activation mechanisms: Modeling,Bayesian estimation,and case influence diagnostics

In this paper we propose a general cure rate aging model. Our approach enables different underlying activation mechanisms which lead to the event of interest. The number of competing causes of the event of interest is assumed to follow a logarithmic distribution. The model is parameterized in terms of the cured fraction which is then linked to covariates. We explore the use of Markov chain Monte Carlo methods to develop a Bayesian analysis for the proposed model. Moreover, some discussions on the model selection to compare the fitted models are given, as well as case deletion influence diagnostics are developed for the joint posterior distribution based on the ψ-divergence, which has several divergence measures as particular cases, such as the Kullback–Leibler (K-L), J-distance, L₁ norm, and χ²-square divergence measures. Simulation studies are performed and experimental results are illustrated based on a real malignant melanoma data.     

Slashed generalized Rayleigh distribution

We introduce a new family of distributions suitable for fitting positive data sets with high kurtosis which is called the Slashed Generalized Rayleigh Distribution. This distribution arises as the quotient of two independent random variables, one being a generalized Rayleigh distribution in the numerator and the other a power of the uniform distribution in the denominator. We present properties and carry out estimation of the model parameters by moment and maximum likelihood (ML) methods. Finally, we conduct a small simulation study to evaluate the performance of ML estimators and analyze real data sets to illustrate the usefulness of the new model.     

The effects of under‐skilling on need for recovery,losing employment and retirement intentions among older office workers: A prospective cohort study

Based on a sample of older workers from the Maastricht Cohort Study, the authors investigate the prevalence and dynamics of self‐reported under‐skilling and its effects on workers' need for recovery, their risk of losing employment and their retirement intentions over a two‐year period. They find that being under‐skilled is associated both with higher levels of need for recovery over time and with the risk of losing employment, but not with early retirement intentions. To achieve sustainable employment, they argue, the course of under‐skilling should be monitored throughout workers' careers, enabling timely interventions to avoid its negative consequences.     

Stagnation only on the surface? The implications of skill and family responsibilities for the gender wage gap in Sweden, 1974–2010

The wage differential between women and men persists in advanced economies despite the inflow of women into qualified occupations in recent years. Using five waves of the Swedish Level‐of‐Living Survey (LNU), this paper explores the gender wage gap in Sweden during the 1974–2010 period overall and by skill level. The empirical analyses showed that the general gender wage gap has been nearly unchanged for the past 30 years. However, the gender difference in wage in less qualified occupations fell considerably, whereas the gender pay gap remained stable for men and women in qualified occupations. The larger significance of family responsibilities for wages in qualified occupations is one likely explanation for this result.     

PEER PRESSURE: EXPERIMENTAL EVIDENCE FROM RESTROOM BEHAVIOR

We provide experimental evidence on the effect of peer pressure on individual behavior. Specifically, we study the effect of being exposed to an observer in a public restroom on handwashing and urinal flushing behavior. Our estimates show that being exposed to an observer increases the probability of handwashing by 13 percentage points and the probability of urinal flushing by 15 percentage points. Given that handwashing and urinal flushing have social benefits that exceed individual benefits, our findings provide support for peer pressure as an additional way of addressing the social suboptimality arising from externalities. (JEL C91, C93)     

Characteristics of Couples Who Attend Family Services Counselor Visits in Relationship Education

Case management services for low-income couples receiving relationship education have been required by federal funding agencies. Studies examining relationship education outcomes for low-income couples have yet to address participant characteristics of those who attend case management services (e.g., distressed vs. nondistressed). Thus, this study examined the influence of baseline relationship satisfaction and demographics on attendance at case management visits for 2,628 low-income, partnered participants who attended relationship education. Findings indicated that participants who reported higher baseline relationship distress attended more family services counselor (FSC) visits. However, when we added demographics to the model, relationship distress no longer predicted FSC visits, whereas income served as a predictor for men and women, with those reporting greater monthly income attending more FSC visits.