Hazard Duration Model Research Articles

Effect of wealth inequality on child and infant mortality in Togo

At birth, individual has a health capital that depends on family, environmental and personal characteristics which depreciates over time requiring investment. It's in this sense that this article aims to analyze the effect of wealth inequality on infant and child mortality in Togo. This effect is accessed by a semi-parametric proportional hazard duration model of Cox. According to the model estimation which is based on data from the Multiple Indicator Cluster Survey (MICS) carried out in Togo in 2017, the results obtained show in one hand that coming from a less wealthy household increases the risk of death for children. On other hand, the results show that the possession of a source of drinking water, the possession of health insurance by the mother, and the mastery of the use of new information technologies and communication reduce the risk of infant and child mortality. In view of these results, policies to reduce wealth inequalities could help reduce the risk of infant and child mortality in proportions ranging from 0.075 to 0.264.

Effet de l'accès aux services de soins de santé sur mortalité infantile au Togo

Cet article vise à analyser les effets d'un accès sans restriction aux soins de santé sur la mortalité infantile au Togo. Nous nous sommes appuyés sur un modèle de duré à risque proportionnel pour évaluer ces effets. A la suite des estimations de ce modèle à partir des données de l'Enquête Démographique et de Santé réalisée au Togo en 2013, nos résultats montrent que naître en présence d'un personnel de santé qualifié contribue à réduire le risque de mortalité des enfants de moins d'un an. Par ailleurs, une amélioration de l'éducation des mères améliore la probabilité de survie des enfants au-delà de leur premier anniversaire. Ce travail permet de souligner la nécessité d'investir dans la formation du personnel soignant et aussi encourager l'éducation des filles. De tels investissements permettront de réduire significativement la mortalité infantile.

Impact of Flextime on Departure Time Choice for Home-Based Commuting Trips in Austin, Texas

An increasing number of corporations and workplaces are providing flexible working hours or flextime for employees, which is expected to reduce congestion by redistributing the temporal pattern of commuters’ departure time. This study examines the impact of flextime on departure time choice using a Bayesian continuous-time hazard duration model. The model accommodates the time-varying effect of covariates and unobserved heterogeneity. Results from the Austin Household Travel Survey collected between 2017 and 2018 show that workers who have a flextime option choose to leave later, with a predominant effect deterring morning peak departures. Other trip and individual-specific variables, such as travelers’ job type, trip duration, number of trips during the travel day, and household income, are found to have significant impacts on departure time choice. The results also show that flextime is more effective in shifting the departure time for retail and service sector employees, for those whose journeys are longer, and for those who perform more daily activities. The findings of this study support the theory that implementing such policies may ease congestion by staggering the travel demand from peak to off-peak hours.

Hazard Duration Model with Panel Data for Daily Car Travel Distance: A Toyota City Case Study

The limitation of battery size for electric vehicles has driven researchers to study driving distance. Trip patterns and traveler preferences in terms of distance are affected by multiple variables. This study, using socioeconomics, weather conditions, and vehicle characteristics as covariates, compares lognormal, log-logistic, and Weibull distribution assumptions on daily car travel distances with a parametric hazard model for both pooled and panel regression. The results reveal that the log-logistic distribution performed best for both the pooled and panel models, and the inclusion of heterogeneity by the panel model improves the model. The results suggest that the travel distances achieved by people in Toyota City, Japan, is highly dependent on the weather conditions, specifically the precipitation and wind speed. Socioeconomic indicators, such as age and gender, and vehicle characteristics, such as engine size and vehicle price, also significantly affect the car travel distance.

Evaluation of machine learning methodologies to predict stop delivery times from GPS data

In last mile distribution, logistics companies typically arrange and plan their routes based on broad estimates of stop delivery times (i.e., the time spent at each stop to deliver goods to final receivers). If these estimates are not accurate, the level of service is degraded, as the promised time window may not be satisfied.The purpose of this work is to assess the feasibility of machine learning techniques to predict stop delivery times. This is done by testing a wide range of machine learning techniques (including different types of ensembles) to (1) predict the stop delivery time and (2) to determine whether the total stop delivery time will exceed a predefined time threshold (classification approach). For the assessment, all models are trained using information generated from GPS data collected in Medellín, Colombia and compared to hazard duration models.The results are threefold. First, the assessment shows that regression-based machine learning approaches are not better than conventional hazard duration models concerning absolute errors of the prediction of the stop delivery times. Second, when the problem is addressed by a classification scheme in which the prediction is aimed to guide whether a stop time will exceed a predefined time, a basic K-nearest-neighbor model outperforms hazard duration models and other machine learning techniques both in accuracy and F1 score (harmonic mean between precision and recall). Third, the prediction of the exact duration can be improved by combining the classifiers and prediction models or hazard duration models in a two level scheme (first classification then prediction). However, the improvement depends largely on the correct classification (first level).

Simulating pre-evacuation times using hazard-based duration models: Is waiting strategy more efficient than instant response?

In an indoor evacuation scenario, an early decision to be made by each occupant is when to initiate the (decisive) evacuation movement, a decision that determines the pre-evacuation (or pre-movement) time. We employ a class of econometric models, proportional hazard duration models, to simulate the probabilistic relation between the pre-movement times and the occupant’s proximity to exits at the onset of evacuations. This is based on the empirically-supported assumption that occupants that are relatively further from exit locations when the evacuation cue is perceived, take relatively longer times to initiate their evacuation movement. Implementing these parametric models and using extensive numerical simulations, we investigate the effects of (various degrees and forms of) pre-movement-time heterogeneity on the evacuation efficiency. This is to revisit and test the anecdotal idea that occupants’ collective instant rush hinders evacuation processes. In testing this assumption, we examined whether heterogeneity (i.e. variation) in pre-movement times can lead to better outcomes (i.e. shorter evacuation times). Our analyses included both purely-random heterogeneity as well as strategized heterogeneity, one in which occupants nearer to exits are prioritised, as a (probabilistic) waiting strategy. We observed that the instant movement of occupants led to bigger crowd jams at bottlenecks and created greater degrees of congestion which sustained for longer amounts of time. However, from a time-minimisation perspective, collective instant movement was invariably the best strategy. Neither the random nor the strategized forms of pre-movement-time heterogeneity resulted in any shorter evacuation time than when all occupants initiated their movement instantly. In fact, increasing the degree of pre-movement-time heterogeneity led monotonically to longer evacuation times, despite making the evacuation more orderly. This finding suggests that advising occupants to avoid instant rush may not be a time-optimal strategy, even though it mitigates congestion. The finding has not been tested in relation to high-rise buildings and needs further investigation in that context.

Activity start time and duration: incorporating regret theory into joint discrete–continuous models

ABSTRACTActivity start time and duration decisions are two key elements of activity-travel behaviour. As an effort towards a more realistic representation of individuals’ decision behaviour, this paper presents a new copula-based joint model of activity start time and duration. We incorporate the regret theory into the joint modelling framework, which assumes that individuals tend to avoid the situation where non-chosen alternatives outperform the chosen one in one or more attributes. The proposed joint model comprises a hybrid utility-regret model as the discrete component to estimate activity start time and a hazard duration model as the continuous component to estimate activity duration. The comparative analysis of estimation results reveals that the proposed structure is statistically superior to the utility-based joint model and independent models. We also found that applying the regret-based decision rule for variables of travel time and travel time variability significantly improves the model.

Job separation rates of immigrants and natives in the UK during the Great Recession

PurposeThe purpose of this paper is to assess the probability of job separations of immigrants and natives in the UK before and during the economic crisis of 2008.Design/methodology/approachA mixed proportional hazard duration model with a semi-parametric piecewise constant baseline hazard is used on a data sample of inflows into employment.FindingsIt is found that the crisis increased the probability of exits to unemployment for all groups, while immigrants from the new countries of the European Union seemed to have the lowest hazard towards unemployment even after controlling for their demographic and labour market characteristics. More specifically, even when we account for the fact that they tend to cluster in jobs that are most vulnerable to the business cycle, they are still less likely to exit dependent employment than natives. However, this migrant group is adversely affected by the crisis the most.Research limitations/implicationsPossible implications of out-migration of the lower performers are discussed.Originality/valueThis paper makes use of the panel element of the UK Quarterly Labour Force Survey, and uses duration analysis on the individual level to assess the labour market outcomes of natives and immigrants in the UK.

Heterogeneous hazard model of PEV users charging intervals: Analysis of four year charging transactions data

Public charging infrastructure represents a key success factor in the promotion of plug-in electric vehicles (PEV). Given that a large initial investment is required for the widespread adoption of PEV, many studies have addressed the location choice problem for charging infrastructure using a priori simple assumptions. Ideally, however, identifying optimal locations of charging stations necessitates an understanding of charging behavior. Limited market penetration of PEV makes it difficult to grasp any regularities in charging behavior. Using a Dutch data set about four-years of charging transactions, this study presents a detailed analysis of inter-charging times. Recognizing that PEV users may exhibit different charging behavior, this study estimates a latent class hazard duration model, which accommodates duration dependence, unobserved heterogeneity and the effects of time-varying covariates. PEV users are endogenously classified into regular and random users by treating charging regularity as a latent variable. The paper provides valuable insights into the dynamics of charging behavior at public charging stations, and which strategies can be successfully used to improve the performance of public charging infrastructure.

Intercity migration in China: a recurrent-event duration analysis of repeat migration

This paper focuses on repeat migration of migrant workers in China. We explore repeat migration from the perspective of the duration of each migration stage in one’s migration history. The main methodology is a recurrent-event Cox proportional hazard (PH) duration model that examines the effects of both time-independent and time-dependent variables on the potential for repeat migration. We also assess the PH assumption for time-independent variables. We find that the age of first migration, the accompaniment of family members and the types and location of destination cities have significant effects on the potential of migrants’ subsequent movements to other cities.

Examination of the Factors Influencing the Clearance Time of Freeway Incidents

AbstractTraffic incidents are the primary cause of delay in urban settings, reducing capacity and creating risks for both motorists and incident response personnel. As incident duration increases, the risk of secondary incidents or crashes also becomes a problem. In response to these issues, many communities have initiated incident management programs aimed at detecting, responding to, and clearing incidents in order to restore freeways to full capacity as quickly and safely as possible. This study involved the development of fully parametric hazard duration models to examine those factors impacting the time required by the Michigan Department of Transportation's Freeway Courtesy Patrol to clear incidents that occurred on the freeway network in metropolitan Detroit. These models were developed using traffic flow data, roadway geometry information, and an extensive incident database. Four fully parametric hazard duration models are developed, each assuming a different underlying probability distribution for the hazard function. In general, each modeling framework provided similar results, though a log- logistic distribution is shown to provide a better fit for the incident clearance data in comparison to other distributions. Various factors were found to significantly affect incident clearance time, including the time of day and time of year at which the incident occurred, the geometric and traffic characteristics of the freeway segment, and the characteristics of the incident.

Examination of factors affecting freeway incident clearance times: a comparison of the generalized F model and several alternative nested models

ABSTRACTTraffic incidents are a principal cause of congestion on urban freeways, reducing capacity and creating risks for both involved motorists and incident response personnel. As incident durations increase, the risk of secondary incidents or crashes also becomes problematic. In response to these issues, many road agencies in metropolitan areas have initiated incident management programs aimed at detecting, responding to, and clearing incidents to restore freeways to full capacity as quickly and safely as possible. This study examined those factors that impact the time required by the Michigan Department of Transportation Freeway Courtesy Patrol to clear incidents that occurred on the southeastern Michigan freeway network. These models were developed using traffic flow data, roadway geometry information, and an extensive incident inventory database. A series of parametric hazard duration models were developed, each assuming a different underlying probability distribution for the hazard function. Although each modeling framework provided results that were similar in terms of the direction of factor effects, there was significant variability in terms of the estimated magnitude of these impacts. The generalized F distribution was shown to provide the best fit to the incident clearance time data, and the use of poorer fitting distributions was shown to result in severe over‐estimation or under‐estimation of factor effects. Those factors that were found to impact incident clearance times included the time of day and month when the incident occurred, the geometric and traffic characteristics of the freeway segment, and the characteristics of each incident. Copyright © 2012 John Wiley & Sons, Ltd.

Benefit shifting: The case of sickness insurance for the unemployed

This study describes the probability of transition from unemployment with unemployment insurance (UI) to sickness insurance (SI), using a proportional hazard duration model and a large register-based dataset. The combination of limited UI duration and the fact that SI rights do not depend on remaining UI, creates an incentive to use SI to effectively extend UI. The separate effects of elapsed unemployment duration and of UI duration on hazard rates are identified through a reform of the UI system. The estimated hazard rate for transition from unemployment to SI increases sharply the last months before UI exhaustion. The spikes are larger for diagnosis for mental illness, and vary across individuals, but are present for all groups and all diagnoses.

Modeling Individuals' Frequency and Time Allocation Behavior for Shopping Activities Considering Household-Level Random Effects

A comprehensive frequency and time allocation modeling system for shopping activities is described. The modeling system is person-based but explicitly considers fixed and random household effects. It has three components: a weekly shopping frequency model, a daily shopping frequency model, and a time allocation model for individual shopping episodes. The frequency models consider activity generation as a latent response—the propensity to participate in shopping activities. This latent response is modeled by using an ordinal response model. Both the weekly and daily frequency models are multilevel ordinal logit models, in which the household is the highest level and the individual is the lowest level. The multilevel ordinal logit models incorporate household-level influences on an individual's shopping behavior in terms of fixed effects and a random intercept. The time allocation models are hazard duration models that consider household-level random heterogeneity. The entire modeling system is sequential f...

Modeling Individuals’ Frequency and Time Allocation Behavior for Shopping Activities considering Household-Level Random Effects

A comprehensive frequency and time allocation modeling system for shopping activities is described. The modeling system is person-based but explicitly considers fixed and random household effects. It has three components: a weekly shopping frequency model, a daily shopping frequency model, and a time allocation model for individual shopping episodes. The frequency models consider activity generation as a latent response—the propensity to participate in shopping activities. This latent response is modeled by using an ordinal response model. Both the weekly and daily frequency models are multilevel ordinal logit models, in which the household is the highest level and the individual is the lowest level. The multilevel ordinal logit models incorporate household-level influences on an individual's shopping behavior in terms of fixed effects and a random intercept. The time allocation models are hazard duration models that consider household-level random heterogeneity. The entire modeling system is sequential from the weekly frequency component to the time allocation component. The outputs of the earlier components enter as inputs to the later components: weekly frequency is the input to the daily frequency model; weekly and daily frequencies are input to the time allocation model.

Bias in Affiliated Sell Analyst Recommendations: a Repeated Hazard Duration Model

Bias in Affiliated Sell Analyst Recommendations: a Repeated Hazard Duration Model

Integration of Qualitative and Quantitative Methodologies Framework and Quick Examples

A framework that integrates qualitative and quantitative data analysis methodologies of trip-chaining behavior research was developed. The proposed qualitative methods include analysis of descriptive statistics and visual analysis of space–time prisms. The results of the qualitative analysis help in the quantitative modeling process. The proposed integrated qualitative and quantitative framework incorporates both logit models and hazard duration models as quantitative analysis tools. Qualitative examples, what was learned from them, and how the qualitative data affect the quantitative methodology are described. The qualitative examples show that aggregate and individual trip-chaining behaviors are not easy to model. Integration of the results from both qualitative and quantitative methods lead to a better understanding of how people make their trip-chaining and travel behavior decisions.

Analysis of Trip and Stop Duration for Shopping Activities: Simultaneous Hazard Duration Model System

A joint hazard-based model for the analysis of simultaneous (mutually interdependent) duration processes is proposed. The proposed model generalizes independent hazard-based models by accounting for correlations between simultaneous duration processes. Furthermore, the model also permits the use of flexible and variable hazard function parameters to capture realistic features observed empirically in activity duration data (e.g., bimodal peaks). To account for correlated processes (duration processes) that underlie observed stop and trip durations, the proposed model relies on an implicit component of error structure that combines a baseline hazard function (log–logistic distribution) with a mixing (log–normal) distribution. This model is estimated by the simulated maximum-likelihood technique and is used to analyze activity and trip duration for shopping activities. The results highlight the need to account for duration dependence effects in activity–travel durations. Furthermore, hazard-based models that disregard correlation across joint duration processes can provide biased estimates and inaccurate forecasts. Empirical results from San Francisco, California (1996), activity diary data imply that stop and trip durations for shopping activities are positively correlated. The hazard rate profile (shape and intensity) also varies significantly across individuals, suggesting the need for targeted demand management measures. At a substantive level, the results indicate the role of personal, household, and situational attributes on activity and trip duration decisions. These findings and models have important applications in the analysis of activity–travel dimensions of duration and timing and the evaluation of alternate travel demand management measures.

Rent control and tenancy duration

This paper investigates how rent control affects mobility in the Danish housing market. We apply a proportional hazard duration model, that encompasses both the presence of left truncated tenancy durations, right censored observations and allows for a very flexible specification of the time dependency of the hazard rate. Tenancy mobility is severely reduced by rent control. For a typical household in the private rental sector tenancy duration is found to be more than six years longer if the apartment belongs to the 10% most regulated units than if it belongs to the 10% least regulated units.

A continuous-time model of departure time choice for urban shopping trips

This paper proposes a continuous-time hazard duration model for urban shopping trip departure time choice. The time frame for the analysis of departure time is the entire day. The continuous-time model uses a non-parametric baseline hazard distribution, employs a non-parametric representation for the time-varying effect of covariates, and accommodates time-varying covariates. These econometric issues are important to recognize and consider in a departure time model spanning the entire day. The model also accommodates unobserved heterogeneity and recognizes the “rounding” of reported departure times by individuals in surveys to an integral multiple of 5 min. The continuous-time model is estimated using shopping trip data from the 1996 activity survey collected in the Dallas-Fort Worth metropolitan area. The effects of individual and household socio-demographics, employment attributes, and trip-related characteristics on departure time choice are presented and discussed. Application of the continuous-time model to forecast temporal shifts in shopping trip-making due to changes in socio-demographic characteristics and trip-chaining behavior is demonstrated. The use of the formulation as a powerful evaluation tool to manage and influence traffic patterns through dynamic congestion pricing control schemes is also highlighted.