In recent years, various authorities launched projects that aim to make their cities more age-friendly. Designing age-friendly cities is a complex and context-dependent process that requires clear implementation guidelines for policy makers. As one of the eight domains of age-friendly cities, transportation is a critical component of making our cities more liveable for older adults and their families. This paper contributes to the literature by exploring the travel behaviour of older adults with a focus on the factors that lead to sustainable mobility patterns. Our empirical analysis is based on survey data collected from 1,221 older adults as part of the Age-Friendly Columbus project in Columbus, Ohio in the United States of America. We develop multinomial logistic regression models to investigate the travel mode choices of older adults (auto only, non-auto options only and multimodal (auto and at least one non-auto option)). We include age and built environment characteristics as the key variables, with lifestyle-related factors and socio-demographics as controls in our analysis. We find older respondents were more likely to use autos only compared to younger respondents. Our analysis also reveals significant associations between built environment characteristics and travel mode choices. Interaction effects show that the relationships between built environment characteristics and travel preferences differed by age cohorts among older individuals. The primary contribution of this study is that it provides evidence on what built environmental improvements help to promote sustainable travel among older adults in mid-sized and auto-dependent metropolitan cities. We argue that these improvements contribute to older adults' sustainable mobility, as well as out-of-home activity behaviour, social engagement and individual health. The results of this study may especially benefit non-driver older adults who lack reliable non-auto alternatives for their daily travel.

Customer churn, which insurance companies use to describe the non-renewal of existing customers, is a widespread and expensive problem in general insurance, particularly because contracts are usually short-term and are renewed periodically. Traditionally, customer churn analyses have employed models which utilise only a binary outcome (churn or not churn) in one period. However, real business relationships are multi-period, and policyholders may reside and transition between a wider range of states beyond that of the simply churn/not churn throughout this relationship. To better encapsulate the richness of policyholder behaviours through time, we propose multi-state customer churn analysis, which aims to model behaviour over a larger number of states (defined by different combinations of insurance coverage taken) and across multiple periods (thereby making use of readily available longitudinal data). Using multinomial logistic regression (MLR) with a second-order Markov assumption, we demonstrate how multi-state customer churn analysis offers deeper insights into how a policyholder’s transition history is associated with their decision making, whether that be to retain the current set of policies, churn, or add/drop a coverage. Applying this model to commercial insurance data from the Wisconsin Local Government Property Insurance Fund, we illustrate how transition probabilities between states are affected by differing sets of explanatory variables and that a multi-state analysis can potentially offer stronger predictive performance and more accurate calculations of customer lifetime value (say), compared to the traditional customer churn analysis techniques.

Level of contraceptive use is one of the primary proximate determinants of fertility level. Among Arab countries, Iraq experiences high fertility rates, especially among adolescents. According to the 2018 Iraq Multiple Indicator Cluster Survey (IMICS 2018), 52.8% of currently married Iraqi women used a contraceptive method (36.1% used modern methods, and 16.7% used traditional methods). A multiple multinomial logistic regression model was adopted to investigate the demographic, socioeconomic, fertility, and cultural determinants of contraceptive use among currently married, nonpregnant Iraqi women based on the 2018 Iraq Multiple Indicator Cluster Survey data. The main findings indicated that women using modern contraceptive methods had more children, did not experience the death of a child, and had no desire for more children. Moreover, they were married before age 21, had at least an upper secondary education, had access to mass media, used the internet, belonged to a low or middle wealth category, and lived in urban Kurdistan. Kurdish women prefer to use traditional methods. The results suggest that family planning programmes should target women who live in southern/central areas of Iraq, as they were the least likely to use contraceptives, and motivate Kurdish women to use modern contraceptives rather than traditional contraceptives.

Knowledge about the association between alcohol and Barrett’s oesophagus and reflux oesophagitis is conflicting. In this case–control study we evaluated the role of specific alcoholic beverages (red and white wine, beer and liquors) in 339 Barrett’s oesophagus and 462 oesophagitis patients compared with 619 endoscopic controls with other disorders, recruited in twelve Italian endoscopic units. Data on alcohol and other individual characteristics were obtained from structured questionnaires. No clear, monotonic significant dose–response relationship was pointed out for red wine. However, a generalised U-shaped trend of Barrett’s oesophagus/oesophagitis risk due to red wine consumption particularly among current drinkers was found. Similar results were also found for white wine. Liquor/spirit consumption seemed to bring about a 1·14–2·30 risk excess, although statistically non-significant, for current Barrett’s oesophagus/oesophagitis drinkers. Statistically significant decreasing dose–response relationships were found in Barrett’s oesophagus for frequency and duration of beer consumption. Similar, but less clear downward tendencies were also found for oesophagitis patients. In conclusion, although often not statistically significant, our data suggested a reduced risk of Barrett’s oesophagus and oesophagitis with a low/moderate intake of wine and beer consumption. A non-significant increased risk of Barrett’s oesophagus/oesophagitis was observed with a higher intake of any type of heavy alcohol consumption, but no conclusion can be drawn owing to the high number of non-spirit drinkers and to the small number of drinkers at higher alcohol intake levels.

The analysis of causal mortality provides rich insight into changes in mortality trends that are hidden in population-level data. Therefore, we develop and apply a multinomial logistic framework to model causal mortality. We use internationally classified cause-of-death categories and data obtained from the World Health Organization. Inherent dependence amongst the competing causes is accounted for in the framework, which also allows us to investigate the effects of improvements in, or the elimination of, cause-specific mortality. This has applications to scenario-based forecasting often used to assess the impact of changes in mortality. The multinomial model is shown to be more conservative than commonly used approaches based on the force of mortality. We use the model to demonstrate the impact of cause-elimination on aggregate mortality using residual life expectancy and apply the model to a French case study.

The authors derive a general equation to compute multiple cut-offs on a total test score in order to classify individuals into more than two ordinal categories. The equation is derived from the multinomial logistic regression (MLR) model, which is an extension of the binary logistic regression (BLR) model to accommodate polytomous outcome variables. From this analytical procedure, cut-off scores are established at the test score (the predictor variable) at which an individual is as likely to be in category j as in category j+1 of an ordinal outcome variable. The application of the complete procedure is illustrated by an example with data from an actual study on eating disorders. In this example, two cut-off scores on the Eating Attitudes Test (EAT-26) scores are obtained in order to classify individuals into three ordinal categories: asymptomatic, symptomatic and eating disorder. Diagnoses were made from the responses to a self-report (Q-EDD) that operationalises DSM-IV criteria for eating disorders. Alternatives to the MLR model to set multiple cut-off scores are discussed.