Negative Binomial Regression Models (negative + binomial_regression_models)

Distribution by Scientific Domains

Selected Abstracts

An investigation of incident frequency, duration and lanes blockage for determining traffic delay

Yi (Grace) Qi
Traffic delay caused by incidents is closely related to three variables: incident frequency, incident duration, and the number of lanes blocked by an incident that is directly related to the bottleneck capacity. Relatively, incident duration has been more extensively studied than incident frequency and the number of lanes blocked in an incident. In this study, we provide an investigation of the influencing factors for all of these three variables based on an incident data set that was collected in New York City (NYC). The information about the incidents derived from the identification can be used by incident management agencies in NYC for strategic policy decision making and daily incident management and traffic operation. In identifying the influencing factors for incident frequency, a set of models, including Poisson and Negative Binomial regression models and their zero-inflated models, were considered. An appropriate model was determined based on a model decision-making tree. The influencing factors for incident duration were identified based on hazard-based models where Exponential, Weibull, Log-logistic, and Log-normal distributions were considered for incident duration. For the number of lanes blocked in an incident, the identification of the influencing factors was based on an Ordered Probit model which can better capture the order inherent in the number of lanes blocked in an incident. As identified in this study, rain is the only factor that significantly influenced incident frequency. For incident duration and the number of lanes blocked in an incident, various factors had significant impact. As concluded in this study, there is a strong need to identify the influencing factors in terms of different types of incidents and the roadways where the incidents occured. [source]

Do Muscle Mass, Muscle Density, Strength, and Physical Function Similarly Influence Risk of Hospitalization in Older Adults?

Peggy Mannen Cawthon PhD
OBJECTIVES: To examine the association between strength, function, lean mass, muscle density, and risk of hospitalization. DESIGN: Prospective cohort study. SETTING: Two U.S. clinical centers. PARTICIPANTS: Adults aged 70 to 80 (N=3,011) from the Health, Aging and Body Composition Study. MEASUREMENTS: Measurements were of grip strength, knee extension strength, lean mass, walking speed, and chair stand pace. Thigh computed tomography scans assessed muscle area and density (a proxy for muscle fat infiltration). Hospitalizations were confirmed by local review of medical records. Negative binomial regression models estimated incident rate ratios (IRRs) of hospitalization for race- and sex-specific quartiles of each muscle and function parameter separately. Multivariate models adjusted for age, body mass index, health status, and coexisting medical conditions. RESULTS: During an average 4.7 years of follow-up, 1,678 (55.7%) participants experienced one or more hospitalizations. Participants in the lowest quartile of muscle density were more likely to be subsequently hospitalized (multivariate IRR=1.47, 95% confidence interval (CI)=1.24,1.73) than those in the highest quartile. Similarly, participants with the weakest grip strength were at greater risk of hospitalization (multivariate IRR=1.52, 95% CI=1.30,1.78, Q1 vs. Q4). Comparable results were seen for knee strength, walking pace, and chair stands pace. Lean mass and muscle area were not associated with risk of hospitalization. CONCLUSION: Weak strength, poor function, and low muscle density, but not muscle size or lean mass, were associated with greater risk of hospitalization. Interventions to reduce the disease burden associated with sarcopenia should focus on increasing muscle strength and improving physical function rather than simply increasing lean mass. [source]

Trends in chronic disease mortality in the Northern Territory Aboriginal population, 1997-2004: using underlying and multiple causes of death

Emily Fearnley
Abstract Objective: To assess trends in chronic disease mortality in the Aboriginal population of the Northern Territory (NT), using both underlying and multiple causes of death. Method: Death registration data from 1997 to 2004, were used for the analysis of deaths from five chronic diseases; ischaemic heart disease (IHD), diabetes, chronic obstructive pulmonary disease (COPD), renal failure and stroke. Negative binomial regression models were used to estimate the average annual change in mortality rates for each of the five diseases. Chi squared tests were conducted to determine associations between the five diseases. Results: The five chronic diseases contributed to 49.3% of all Aboriginal deaths in the NT. The mortality rate ratio of NT Aboriginal to all Australian death rates from each of the diseases ranged from 4.3 to 13.0, with the lowest rate ratio for stroke and highest for diabetes. There were significant statistical associations between IHD, diabetes, renal failure and stroke. The mortality rates for diabetes, COPD and stroke declined at estimated annual rates for NT Aboriginal males of 3.6%, 1.0% and 11.7% and for Aboriginal females by 3.5%, 6.1% and 7.1% respectively. There were increases in mortality rates for Aboriginal males and females for IHD and a mixed result for renal failure. Conclusion: NT Aboriginal people experience high chronic disease mortality, however, mortality rates appear to be declining for diabetes, COPD and stroke. The impact of chronic disease on mortality is greater than previously reported by using a single underlying cause of death. The results highlight the importance of integrated chronic disease interventions. [source]

Social vulnerability and the natural and built environment: a model of flood casualties in Texas

DISASTERS, Issue 4 2008
Sammy Zahran
Studies on the impacts of hurricanes, tropical storms, and tornados indicate that poor communities of colour suffer disproportionately in human death and injury., Few quantitative studies have been conducted on the degree to which flood events affect socially vulnerable populations. We address this research void by analysing 832 countywide flood events in Texas from 1997,2001. Specifically, we examine whether geographic localities characterised by high percentages of socially vulnerable populations experience significantly more casualties due to flood events, adjusting for characteristics of the natural and built environment. Zero-inflated negative binomial regression models indicate that the odds of a flood casualty increase with the level of precipitation on the day of a flood event, flood duration, property damage caused by the flood, population density, and the presence of socially vulnerable populations. Odds decrease with the number of dams, the level of precipitation on the day before a recorded flood event, and the extent to which localities have enacted flood mitigation strategies. The study concludes with comments on hazard-resilient communities and protection of casualty-prone populations. [source]