Counts data with excessive zeros are frequently encountered in practice. For example, the number of health services visits often includes many zeros representing the patients with no utilization during a follow-up time. A common feature of this type of data is that the count measure tends to have excessive zero beyond a common count distribution can accommodate, such as Poisson or negative binomial. Zero-inflated or hurdle models are often used to fit such data. Despite the increasing popularity of ZI and hurdle models, there is still a lack of investigation of the fundamental differences between these two types of models. In this article, we reviewed the zero-inflated and hurdle models and highlighted their differences in terms of their data generating processes. We also conducted simulation studies to evaluate the performances of both types of models. The final choice of regression model should be made after a careful assessment of goodness of fit and should be tailored to a particular data in question.

Air pollution in Beijing, especially PM2.5, has received increasing attention in the past years. Although exposure to PM2.5 has been linked to many health issues, few studies have quantified the impact of PM2.5 on the risk of influenza-like illness (ILI). The aim of our study is to investigate the association between daily PM2.5 and ILI risk in Beijing, by means of a generalized additive model. Daily PM2.5, meteorological factors, and influenza-like illness (ILI) counts during January 1, 2008 to December 31, 2014 were retrieved. An inverse Gaussian generalized additive model with log link function was used to flexibly model the nonlinear relationship between the PM2.5 (single- and multiday lagged exposure) and ILI risk, adjusted for the weather conditions, seasonal and year trends. We also assessed if the effect of PM2.5 differs during flu season versus non-flu season by including the interaction term between PM2.5 and flu season in the model. Furthermore, a stratified analysis by age groups was conducted to investigate how the effect of PM2.5 differs across age groups. Our findings suggested a strong positive relationships between PM2.5 and ILI risk at the flu season (October-April) (p-value < 0.001), after adjusting for the effects of ambient daily temperature and humidity, month and year; whereas no significant association was identified at the non-flu season (May-September) (p-value = 0.174). A short term delayed effect of PM2.5 was also identified with 2-day moving average (current day to the previous day) of PM2.5 yielding the best predictive power. Furthermore, PM2.5 was strongly associated with ILI risk across all age groups (p-value < 0.001) at the flu season, but the effect was the most pronounced among adults (age 25–59), followed by young adults (age 15–24), school children (age 5–14) and the elderly (age 60+) and the effect of PM2.5 was the least pronounced for children under 5 years of age (age < 5). Ambient PM2.5 concentrations were significantly associated with ILI risk in Beijing at the flu season and the effect of PM2.5 differed across age groups, in Beijing, China.

Background: Examining residuals is a crucial step in statistical analysis to identify the discrepancies between models and data, and assess the overall model goodness-of-fit. In diagnosing normal linear regression models, both Pearson and deviance residuals are often used, which are equivalently and approximately standard normally distributed when the model fits the data adequately. However, when the response vari*able is discrete, these residuals are distributed far from normality and have nearly parallel curves according to the distinct discrete response values, imposing great challenges for visual inspection.Methods: Randomized quantile residuals (RQRs) were proposed in the literature by Dunn and Smyth (1996) to circumvent the problems in traditional residuals. However, this approach has not gained popularity partly due to the lack of investigation of its performance for count regression including zero-inflated models through simulation studies. Therefore, we assessed the normality of the RQRs and compared their performance with traditional residuals for diagnosing count regression models through a series of simulation studies. A real data analysis in health care utilization study for modeling the number of repeated emergency department visits was also presented.Results: Our results of the simulation studies demonstrated that RQRs have low type I error and great statistical power in comparisons to other residuals for detecting many forms of model misspecification for count regression models (non-linearity in covariate effect, over-dispersion, and zero inflation). Our real data analysis also showed that RQRs are effective in detecting misspecified distributional assumptions for count regression models.Conclusions: Our results for evaluating RQRs in comparison with traditional residuals provide further evidence on its advantages for diagnosing count regression models.

Maternal depression and anxiety have distinct constellations of symptom trajectories, which are associated with factors that may vary between different groups of women. The aim of this study was to identify subgroups of women who exhibit unique longitudinal trajectory patterns of depressive and anxiety symptoms from pregnancy to 5 years postpartum and the antenatal predictors associated with these maternal groups. The study used a longitudinal data collected from 615 women in Saskatchewan from pregnancy to 5 years postpartum. Semiparametric group-based models were used to identify latent maternal depressive and anxiety trajectory groups. Multinomial logit models were then used to assess the association between maternal characteristics and the identified latent trajectory groups. We identified four trajectory groups of maternal depressive symptoms: low-stable (35%); moderate-stable (54%); moderate-increasing (5%); and high-decreasing (6%), and three trajectory groups of maternal anxiety symptoms: very low-stable (13%); low-stable (58%); and moderate-stable (29%). We also identified several risk factors, most notably history of depression and stress, that were significantly associated with these trajectories. History of depression and increased stress are significant risk factors that can be identified during regular perinatal visits; therefore, clinicians should inquire about these risk factors to identify women at high risk of ongoing depression or anxiety.

Many women still deliver outside a health facility in Ghana, often under unhygienic conditions and without skilled birth attendants. This study aims to examine the social determinants influencing the use of health facility delivery among reproductive-aged women in Ghana. Nationally representative data from the 2014 Ghana Demographic and Health Survey was used to fit univariable and multivariable logistic regression models to estimate the influence of the social determinants on health facility delivery. Andresen’s health care utilization model was used as the conceptual framework guiding this study.. Only 72% of deliveries take place at a health facility in Ghana. The results of the adjusted model indicate that place of residence, financial status, education, religion, parity and perceived need were significantly associated with health facility delivery. First, urban women had a higher likelihood of health facility delivery than rural women (Adjusted Odds ratio [AOR] =2.21; 95% Confidence interval [CI] = 1.53–3.19). Second, middle-class and rich women were 1.57 (95%CI = 1.18–2.08) times and 6.91 (95%CI = 4.12–11.59) times, respectively more likely to deliver at health facility compared to the poor. Third, women with either at least secondary education (AOR = 2.04; 95%CI = 1.57–2.64) or primary education (AOR = 1.39, 95%CI = 1.02–1.92) were more likely to deliver at health facility than women with no education. In terms of parity, first time mothers were 1.58 (95% CI = 1.18–2.12) times more likely to deliver at health facility than those who had given birth three or more times before. Finally, regarding perceived need, women who were aware of pregnancy complications were 1.32 (95%CI = 1.02–1.70) times more likely to use health facility delivery than those who were not informed about pregnancy complications. First, in spite of Ghana’s free maternal health services policy, poorer women were much less likely to have a health facility delivery, which points to the need to understand the indirect costs and other financial barriers preventing women from delivering at a health facility. Second, many of the identified variables influence the demand and not just the supply for health care services, and highlight the importance of the social determinants of health and investments in interventions that extend beyond improving physical access.

Refugee women are almost five times more likely to develop postpartum depression than Canadian-born women. This can be attributed to various difficulties they faced before coming to Canada as well as during resettlement. Moreover, refugee women usually face many obstacles when accessing health services, including language and cultural barriers, as well as unique help-seeking behaviors that are influenced by various cultural and practical factors. There has been a recent, rapid influx of Syrian refugees to Canada, and many of them are childbearing women. However, little is known about the experiences that these women have encountered pre- and post-resettlement, and their perceptions of mental health issues. Thus, there is an urgent need to understand refugee women’s experiences of having a baby in Canada from a mental health perspective. A mixed methods research design included 12 Syrian refugee women who migrated to Saskatoon in 2015–16 and who were either pregnant or 1 year postpartum. The data were collected during a single focus group discussion and a structured questionnaire. Our results showed that more than half of participants have depressive symptoms, half of them have anxiety symptoms, and one sixth have PTSD symptoms. Three major themes emerged from the qualitative data: 1) Understanding of maternal depression; 2) Protective factors for mental health; and 3) Barriers to mental health services. Maternal depression is an important feature in Syrian refugee women recently resettled in Canada. Reuniting these women with their families and engaging them in culturally appropriate support programs may improve their mental health outcomes.