Marginal zero-inflated regression models for count data

Data sets with excess zeroes are frequently analyzed in many disciplines. A common framework used to analyze such data is the zero-inflated (ZI) regression model. It mixes a degenerate distribution with point mass at zero with a non-degenerate distribution. The estimates from ZI models quantify the effects of covariates on the means of latent random variables, which are often not the quantities of primary interest. Recently, marginal zero-inflated Poisson (MZIP; Long et al. [A marginalized zero-inflated Poisson regression model with overall exposure effects. Stat. Med. 33 (2014), pp. 5151–5165]) and negative binomial (MZINB; Preisser et al., 2016) models have been introduced that model the mean response directly. These models yield covariate effects that have simple interpretations that are, for many applications, more appealing than those available from ZI regression. This paper outlines a general framework for marginal zero-inflated models where the latent distribution is a member of the exponential dispersion family, focusing on common distributions for count data. In particular, our discussion includes the marginal zero-inflated binomial (MZIB) model, which has not been discussed previously. The details of maximum likelihood estimation via the EM algorithm are presented and the properties of the estimators as well as Wald and likelihood ratio-based inference are examined via simulation. Two examples presented illustrate the advantages of MZIP, MZINB, and MZIB models for practical data analysis.     

Evaluating the causal economic impacts of transport investments: evidence from the Madrid–Barcelona high speed rail corridor

This paper evaluates economic impacts arising from the introduction of high-speed rail (HSR) between Madrid and Barcelona. Using difference-in-differences estimation we estimate an average treatment effect for provinces with stops on the HSR line of 2.4% for economic output, 3.3% for numbers of firms, and 1.1% for labour productivity. We complement our DID results with a synthetic control analysis for Lleida and Tarragona, two provinces that we argue were assigned HSR stations largely due to their incidental location. We find that both the number of firms and labour productivity are substantially higher in these provinces than in their synthetic counterparts.     

Cognitive distortions predict future gambling involvement

Disordered gambling is best conceptualized as a continuum of severity. Previous research has demonstrated the utility of studying individuals at all points of this spectrum. The sequence of the development of gambling problems and change in gambling involvement along this continuum of severity is not well understood. The present study examined the interplay between cognitive distortions and gambling involvement in a population sample recruited in Alberta, Canada. Data from 1372 participants over 4 assessment waves (5 years) were used to generate a 2-factor latent structure using gambling fallacies and gambling involvement measurements. Structural equation modelling showed that cognitive distortions more strongly predicted future gambling involvement than the reverse relationship, using the comparative fit index (CFI) and the root mean square error of approximation (RMSEA) to assess the models. In addition, cognitive distortions declined over time, whereas gambling involvement remained stable. The results of the study suggest that focusing primarily on cognitive mechanisms in public health initiatives for gambling disorders may be a more effective strategy than focusing on behavioural solutions.     

Temporal Responsiveness in Mother–Child Dialogue: A Longitudinal Analysis of Children with Normal Hearing and Hearing Loss

Dialogue between conversational partners, including mothers and their children, is precisely timed. The predictability of this timing is important for establishing and maintaining interaction, communication, and learning. This longitudinal study examines changes in the response latency of utterances in dialogue between mothers and their normal hearing and hearing‐impaired children between 4 and 60 months of age. Mothers and their children showed parallel developmental trends, responding to each other more quickly at older ages. Beyond these age‐related group effects, significant dyadic effects were found in which individual children's latencies were related to those of their mothers, and vice versa. Developmental patterns did not significantly differ across hearing status groups, which may reflect the role of early identification and intervention in promoting positive developmental outcomes.     

Overcoming the ‘tyranny of the urgent’: integrating gender into disease outbreak preparedness and response

ABSTRACT

This article contributes to discussions on the gender dimensions of disease outbreaks, and preparedness policies and responses, by providing a multi-level analysis of gender-related gaps, particularly illustrating how the failure to challenge gender assumptions and incorporate gender as a priority at the global level has national and local impacts. The implications of neglecting gender dynamics, as well as the potential of equity-based approaches to disease outbreak responses, is illustrated through a case study of the Social Enterprise Network for Development (SEND) Sierra Leone, a non-government organisation (NGO) based in Kailahun, during the Ebola outbreak.     

Measuring stakeholder identification with nonprofit causes: the development and validation of the identification with social causes scale

Nonprofit organizations (NPOs) achieve desired outcomes by fostering organizational identification. However, little research has explored how identification with the cause or the recipients of support relates to identification with the NPO. This study developed the Identification with Social Causes Scale as a mechanism for distinguishing organizational identification from identification with a social group or cause. Data were collected using two groups: the homeless (n = 318) and HIV positive (n = 314) individuals. Exploratory factor analysis and multigroup confirmatory factor analysis yielded a 9-item scale measuring two dimensions: attachment and consubstantiality. Initial construct validity of the scale was established.