Bayesian semi-parametric analysis of Poisson change-point regression models: application to policy-making in Cali,Colombia

A Poisson regression model with an offset assumes a constant baseline rate after accounting for measured covariates, which may lead to biased estimates of coefficients in an inhomogeneous Poisson process. To correctly estimate the effect of time-dependent covariates, we propose a Poisson change-point regression model with an offset that allows a time-varying baseline rate. When the non-constant pattern of a log baseline rate is modeled with a non-parametric step function, the resulting semi-parametric model involves a model component of varying dimensions and thus requires a sophisticated varying-dimensional inference to obtain the correct estimates of model parameters of a fixed dimension. To fit the proposed varying-dimensional model, we devise a state-of-the-art Markov chain Monte Carlo-type algorithm based on partial collapse. The proposed model and methods are used to investigate the association between the daily homicide rates in Cali, Colombia, and the policies that restrict the hours during which the legal sale of alcoholic beverages is permitted. While simultaneously identifying the latent changes in the baseline homicide rate which correspond to the incidence of sociopolitical events, we explore the effect of policies governing the sale of alcohol on homicide rates and seek a policy that balances the economic and cultural dependencies on alcohol sales to the health of the public.     

Maximum likelihood inference for mixtures of skew Student-t-normal distributions through practical EM-type algorithms

This paper deals with the problem of maximum likelihood estimation for a mixture of skew Student-t-normal distributions, which is a novel model-based tool for clustering heterogeneous (multiple groups) data in the presence of skewed and heavy-tailed outcomes. We present two analytically simple EM-type algorithms for iteratively computing the maximum likelihood estimates. The observed information matrix is derived for obtaining the asymptotic standard errors of parameter estimates. A small simulation study is conducted to demonstrate the superiority of the skew Student-t-normal distribution compared to the skew t distribution. The proposed methodology is particularly useful for analyzing multimodal asymmetric data as produced by major biotechnological platforms like flow cytometry. We provide such an application with the help of an illustrative example.     

Degradation modeling based on gamma process models with random effects

The random effects in a gamma process are introduced in terms of its scale parameter. However, the scale parameter affects both its mean and variance. Hence, the variation of the degradation rates and the within degradation increments are expected to be large. For some products, the random effects affect just the rate or just the volatility of the process. Thus, two modifications of the parameters' structure of the gamma process are proposed. One implies that the random effects affect just the volatility and the second just the rate. A Bayesian estimation approach is provided and implemented in two case studies.     

Dependence maps: Local dependence in practice

There is often more structure in the way two random variables are associated than a single scalar dependence measure, such as correlation, can reflect. Local dependence functions such as that of Holland and Wang (1987) are, therefore, useful. However, it can be argued that estimated local dependence functions convey information that is too detailed to be easily interpretable. We seek to remedy this difficulty, and hence make local dependence a more readily interpretable practical tool, by introducing dependence maps. Via local permutation testing, dependence maps simplify the estimated local dependence structure between two variables by identifying regions of (significant) positive, (not significant) zero and (significant) negative local dependence. When viewed in conjunction with an estimate of the joint density, a comprehensive picture of the joint behaviour of the variables is provided. A little theory, many implementational details and several examples are given.     

Tests for cycling in a signalling pathway

Summary.  Cellular signalling pathways, mediating receptor activity to nuclear gene activation, are generally regarded as feed forward cascades. We analyse measured data of a partially observed signalling pathway and address the question of possible feed-back cycling of involved biochemical components between the nucleus and cytoplasm. First we address the question of cycling in general, starting from basic assumptions about the system. We reformulate the problem as a statistical test leading to likelihood ratio tests under non-standard conditions. We find that the modelling approach without cycling is rejected. Afterwards, to differentiate two different transport mechanisms within the nucleus, we derive the appropriate dynamical models which lead to two systems of ordinary differential equations. To compare both models we apply a statistical testing procedure that is based on bootstrap distributions. We find that one of both transport mechanisms leads to a dynamical model which is rejected whereas the other model is satisfactory.     

The stress of driving: A diary study

A study of daily behaviours and feelings while driving was carried out with a sample of drivers to ascertain driving stress levels and changes in these as a function of time of day and day of the week. The analysis of responses to a specially designed diary/checklist showed that drivers experience more stress in the evening than in the morning, and in mid-week than either at the beginning or end of the week. Daily driving stress varies with age and experience as well as with health condition and sleep quality. It is also related to driving conditions and depends upon people's overall perception of driving as a stressful activity.     

Sample size choice for reliability verification in strength-stress models

This paper discusses the choice of sample size for experiments concerned with inference on R = P(Y < X), where X and Y are normal variates, in an acceptance-sampling-theory framework. A conservative approach is derived, and the properties of this solution examined by simulation.     

Time demands on families: Is there a bottom line?

As families continue to adapt to interpersonal and marketplace pressures, time available for household production is becoming scarce. The purpose of the study reported here is to explore the utility of regional economic analyses in determining minimal levels of household production as measured in terms of time. The results provide a minimum family time required in the long term of approximately 35 hours per week and a short term requirement of 2 hours per week. Theoretical frameworks used in family science are integrated in the discussion to explain these findings.Pamela N. Olson is an Assistant Professor in the Department of Counseling and Family Studies, University of New Mexico, Albuquerque, NM 87131. Her current research interests are family member time-use and families in debt. She completed her Ph.D. at Oregon State University.James J. Ponzetti, Jr. received his Ph.D. from Oregon State University. He is currently an Assistant Professor in Family Studies in the Department of Home Economics, Central Washington University, Ellensburg, WA 98926. His current research interests include divorce, loneliness, and family planning.Geraldine I. Olson is Associate Professor and Graduate Program Director, Family Resource Management, College of Home Economics, Oregon State University, Corvallis, OR 97131. She completed her Ph.D. at The Ohio State University and current research interests include family member time-use, assessing managerial activities, and factors which influence the substitution of marketplace goods with household production.     

Divorced Parents’ Qualitative and Quantitative Reports of Children's Living Arrangements

We use data from a sample of divorced parents in Wisconsin (N = 1,392) to examine how parents describe their children's living arrangements. When the children spend substantial time in both parents’ homes, both parents are less likely to use the phrase live with to describe living arrangements. When children spend most nights with their mother, mothers are more likely than fathers to state that the children live with their mother. Together, these findings suggest that family researchers no longer can rely on simple questions to capture complex living arrangements. We need clearer and more careful question wording and, in some instances, follow‐up questions to accurately describe where children live.