Academic literature on the topic 'Log-binomial model'

Abstract This chapter discusses the use of offsets to account for heterogeneity in the sampling effort and incidence in count GLMs. The use of offsets is related to modeling counts or rates using the Poisson and negative binomial distributions. It goes on to discuss log-linear models as special cases of count GLMs, and provides a detailed example of model selection using a log-linear model. All statistical models are fitted in both the frequentist and Bayesian frameworks.

Abstract This chapter starts by discussing the Poisson and negative binomial distributions to model counts, and the associated log link function. It discusses over-dispersion, a common problem arising in the modeling of counts, along with its consequences and solutions. It illustrates the use of the negative binomial distribution as a continuous Poisson–gamma mixture to deal with over-dispersion, and finally covers the use of mixture models to model counts with an excess of zeros in the two main cases: zero-inflated and zero-augmented models. All the statistical models are fitted in both the frequentist and Bayesian frameworks.

Abstract This chapter starts by discussing the use of the binomial distribution to model binary response variables. It then defines odds, log odds, and the logit link function involved in binary GLMs, and discusses grouped and ungrouped binary analyses in relation to the formatting of the data. It has a strong focus on the interpretation of the fitted parameters of binary GLMs, and discusses the assessment of the goodness of fit of binary GLMs, including the calculation and interpretation of receiver operating curves and the area under the curve, the use of Brier scores, and of the randomized quantile residuals. All statistical models are fitted in both the frequentist and Bayesian frameworks.

We seek to develop a distribution to model the extreme damages resulting from Natural Disasters in Kenya.The distribution is based on the Compound Extreme Value Distribution, which takes into account both the distributions of the frequency of occurrence and magnitude of the events. Threshold modelling is employed, where the extreme damages are identified as the points that lie above a sufficiently high threshold. The distribution of the number of the exceedance is found to be Negative Binomial, while that of the severity is approximated by a Generalised Pareto Distribution. Maximum likelihood estimation is used to estimate the parameters, and the log-likelihood is maximised using numerical methods. Probability weighted moments estimation is used to determine the starting values for the iterations. Prediction study is then carried out to investigate the performance of the proposed distribution in predicting future events.

OBJECTIVES Young women who are sexual minorities (eg, bisexual and lesbian) are approximately twice as likely as those who are heterosexual to have a teen pregnancy. Therefore, we hypothesized that risk factors for teen pregnancy would vary across sexual orientation groups and that other potential risk factors exist that are unique to sexual minorities. METHODS We used multivariable log-binomial models gathered from 7120 young women in the longitudinal cohort known as the Growing Up Today Study to examine the following potential teen pregnancy risk factors: childhood maltreatment, bullying victimization and perpetration, and gender nonconformity. Among sexual minorities, we also examined the following: sexual minority developmental milestones, sexual orientation–related stress, sexual minority outness, and lesbian, gay, and bisexual social activity involvement. RESULTS Childhood maltreatment and bullying were significant teen pregnancy risk factors among all participants. After adjusting for childhood maltreatment and bullying, the sexual orientation–related teen pregnancy disparities were attenuated; these risk factors explained 45% of the disparity. Among sexual minorities, reaching sexual minority developmental milestones earlier was also associated with an increased teen pregnancy risk. CONCLUSIONS The higher teen pregnancy prevalence among sexual minorities compared with heterosexuals in this cohort was partially explained by childhood maltreatment and bullying, which may, in part, stem from sexual orientation–related discrimination. Teen pregnancy prevention efforts that are focused on risk factors more common among young women who are sexual minorities (eg, childhood maltreatment, bullying) can help to reduce the existing sexual orientation–related teen pregnancy disparity.

Right-turn lane (RTL) crashes are among the most key contributors to intersection crashes in the US. Different right turn lanes based on their design, traffic volume, and location have varying levels of crash risk. Therefore, engineers and researchers have been looking for alternative ways to improve the safety and operations for right-turn traffic. This study investigates the traffic safety performance of the RTL in Indiana state based on multi-sources, including official crash reports, official database, and field study. To understand the RTL crashes' influencing factors, we introduce a rand