Search

This paper extends the work of Baltagi et al. (2018) to the popular dynamic panel data model. We investigate the robustness of Bayesian panel data models to possible misspecication of the prior distribution. The proposed robust Bayesian approach departs from the standard Bayesian framework in two ways. First, we consider the ε-contamination class of prior distributions for the model parameters as well as for the individual effects. Second, both the base elicited priors and the ε-contamination priors use Zellner (1986)'s g-priors for the variance-covariance matrices. We propose a general "toolbox" for a wide range of specifications which includes the dynamic panel model with random effects, with cross-correlated effects à la Chamberlain, for the Hausman-Taylor world and for dynamic panel data models with homogeneous/heterogeneous slopes and cross-sectional dependence. Using a Monte Carlo simulation study, we compare the nite sample properties of our proposed estimator to those of standard classical estimators. The paper contributes to the dynamic panel data literature by proposing a general robust Bayesian framework which encompasses the conventional frequentist specications and their associated estimation methods as special cases.

Background: Adult studies have shown that nursing overtime and unit overcrowding is associated with increased adverse patient events but there exists little evidence for the Neonatal Intensive Care Unit (NICU). Objectives: To predict the onset on nosocomial infections and medical accidents in a NICU using machine learning models. Subjects: Retrospective study on the 7,438 neonates admitted in the CHU de Québec NICU (capacity of 51 beds) from 10 April 2008 to 28 March 2013. Daily administrative data on nursing overtime hours, total regular hours, number of admissions, patient characteristics, as well as information on nosocomial infections and on the timing and type of medical errors were retrieved from various hospital-level datasets. Methodology: We use a generalized mixed effects regression tree model (GMERT) to elaborate predictions trees for the two outcomes. Neonates' characteristics and daily exposure to numerous covariates are used in the model. GMERT is suitable for binary outcomes and is a recent extension of the standard tree-based method. The model allows to determine the most important predictors. Results: DRG severity level, regular hours of work, overtime, admission rates, birth weight and occupation rates are the main predictors for both outcomes. On the other hand, gestational age, C-Section, multiple births, medical/surgical and number of admissions are poor predictors. Conclusion: Prediction trees (predictors and split points) provide a useful management tool to prevent undesirable health outcomes in a NICU.

The paper investigates the effects of nursing overtime on nosocomial infections and medical accidents in a neonatal intensive care unit (NICU). The literature lacks clear evidence on this issue and we conjecture that this may be due to empirical and methodological factors. We thus focus on a single NICU, thereby removing much variation in specialty mixes such neonatologists, fellows, residents, nurse practitioners that are observed across units. We model the occurrences of both outcomes using a sample of 3,979 neonates which represents over 84,846 observations (infant/days). We use a semiparametric panel data Logit model with random coefficients. The non-parametric components of the model allow to unearth potentially highly non-linear relationships between the outcomes and various policy-relevant covariates. We use the mean field variational Bayes approximation method to estimate the models. Our results show unequivocally that both health outcomes are affected by nursing overtime. Furthermore, they are both highly sensitive to infant and NICU-related characteristics.