Resena de la obra de Don A. Dillman, Jolene D. Smyth y Leah Melani Christian: Internet, Phone, Mail and Mixed-Mode Surveys. The Tailored Design Method. New Jersey: John Wiley and Sons

https://dialnet.unirioja.es/descarga/articulo/7287796.pdf

Internet, phone, mail and mixed-mode surveys: the tailored design method: reseña

The purpose of this paper is to demonstrate that the scheduling of activities by consumers can be explicitly modeled in theoretically satisfactory and empirically productive way. Even in the case of urban work trips, probably one of the most tightly constrained of everyday activities, schedule shifting is found to be of quantitative importance for the understanding of urban transportation systems. Considerable effort will be required to assess fully the implications of this type of behavior for such important areas of transportation analysis as demand studies, value-of-time measurement, policy simulation, and cost-benefit analysis. Meanwhile, it seems likely that this approach can be applied productively to other goods subject to peak demands.

The scheduling of consumer activities: work trips

The field of travel demand analysis has traditionally been dominated by statistical models. Conversely, Machine Learning (ML) techniques have been rapidly emerging in the past few years, and several studies have demonstrated instances where ML outperformed statistical models, notably in their forecasting potential. In this article, we compare the performance of discrete, continuous, and joint discrete-continuous statistical models with the performance of the neural networks (NN), recognized as a popular ML technique. Specifically, we model two critical trip-related decisions of travel mode and departure time. Overall, we find that in addition to having a much easier and faster implementation process, the NN model offers better predictions for both decision variables. Nonetheless, critiques of NN usually typecast it as a black box due to difficulty of assessing the role of explanatory variables in estimating the target variables. To tackle this issue, we further investigate the contribution of exploratory variables in two steps: (1) estimating the relative importance of each exploratory variable, and (2) conducting sensitivity analysis on the most important variables. The results indicate that beside superior prediction accuracy, the NN is capable of capturing nonlinearities in travel demand, which suggests that it can also be more accurate to capture asymmetrical and non-linear responses for policy analysis purposes.

Modeling travel mode and timing decisions: Comparison of artificial neural networks and copula-based joint model

It is well known that faster and less-expensive transit systems with shorter walking distances, as well as less transfers, are associated with transit use. In this regard, recent studies have focused on estimating transit’s competitiveness and further suggested possible policy interventions. However, there were not much attention on measuring travel time and cost differences between transit and auto by considering the temporal variability. In addition, only a limited study have focused on the impact of either walking during transfers on mode choice or the stage of walking that most affects mode choice. This paper provides additional insights into the impact of travel time, cost, and transit burdens on commute mode choice based on the analysis in a transit-oriented mega city, Seoul, Korea. Together with the 2016 household travel survey data, we utilize the web-based route guide information to measure time, cost, and transit burdens for both chosen and non-chosen modes. The results reveal that commuters are significantly affected by the travel time and cost difference between modes. Additionally, the results indicate that the odds of driving increases by 4.7% and 24.3% when commuters have to transfer once or more than once, respectively. Also, commuters were mostly disinclined to walk longer distances during transfer and egress. The effect of time, cost, and transit burdens on mode choice also varied by income and age groups, further implying the group of people that should be focused when devising policies to encourage transit use. To conclude, this paper suggests potential levers for transportation policies to trigger modal shifts toward sustainable modes by using advanced data sources that better estimate the travel characteristics by departure time based on a point-to-point travel survey data.

Unraveling the impact of travel time, cost, and transit burdens on commute mode choice for different income and age groups

One of the major objectives of this study is to provide more realistic and accurate results related to transit passenger’s route choice behavior by using population data of revealed preference from smartcard transaction records. The smartcard data of the Seoul city provides both boarding and alighting location and time, which can make possible to trace each passenger’s actually used path trajectory with close to 100% market penetration of smartcard usage. This study built an abstract transit network with representative nodes by aggregating all near-by bus stops within walkable distance and with abstract paths by aggregating lines for a specific OD pair that run the same trajectory links by same transit modes. This complex and huge-scale transit network allowed to analyze the route choice behavior of transit passengers in a multimodal transit system that could not be found from the data of relatively small-size cities. This study selected OD pairs which had two or more alternative paths in order to analyze choice behavior requiring a plural alternative choice set. The number of the selected OD pairs are 124,393 pairs that are 33.9% of whole OD pairs that has two or more trip records. The calibration result showed that it is good statistically and logically to include the six explanatory variables in the utility function of the multinomial Logit model. Those are in-vehicle travel time, out-of-vehicle travel time, transfer penalty index, travel time reliability measure, and path circuity index.

Calibration of a transit route choice model using revealed population data of smartcard in a multimodal transit network

Measuring users’ satisfaction of the road network using structural equation modeling

To improve the level of service of traffic and predict travel demand, it is essential to analyze the behavioral factors that affect transportation mode choice and route choice at the individual level. Such analysis requires detailed data on the behavior of people in the selection of different modes and routes. This paper presents a unique data collection endeavor, intended to observe the formation of the choice set from which the final alternative is selected. The revealed preference information about the routes people considered and used for their last work or study trip was targeted. Google Maps API (application programming interface), which has the capacity to calculate and return car and public transportation routes, was employed to program the survey and adaptively show the respondents the routes according to the reported origin and destination. A pilot survey was conducted with this survey tool at the University of New South Wales, Sydney, Australia, with a sample of 200 respondents. A preliminary analysis was carried out to analyze the effectiveness of the survey tool and the specification of the choice set. Three modeling structures—multinomial logit (MNL), nested logit, and mixed MNL—were used to estimate the parameters of the preliminary analysis. The results were fairly intuitive as far as the signs of the parameters were concerned, and travel time significantly influenced route choice.

Choice Set Formation Behaviour: A Joint Mode and Route Choice Selection Model

To improve the level of service of traffic and predict travel demand, it is essential to analyze the behavioral factors that affect transportation mode choice and route choice at the individual level. Such analysis requires detailed data on the behavior of people in the selection of different modes and routes. This paper presents a unique data collection endeavor, intended to observe the formation of the choice set from which the final alternative is selected. The revealed preference information about the routes people considered and used for their last work or study trip was targeted. Google Maps API (application programming interface), which has the capacity to calculate and return car and public transportation routes, was employed to program the survey and adaptively show the respondents the routes according to the reported origin and destination. A pilot survey was conducted with this survey tool at the University of New South Wales, Sydney, Australia, with a sample of 200 respondents. A preliminary a...

Choice Set Formation Behavior: Joint Mode and Route Choice Selection Model:

This paper presents the joint analysis of departure time choice for non-work activities and latent preferences toward the active and non-active mode. Utilizing the concept of smart growth design of...

Incorporating active and non-active mode preferences for Departure time choice behavior

One of the major challenges associated with the analysis of route choice modeling is the formulation of the choice set of alternatives that may allow a relatively accurate prediction of demand for travel routes. The subset of route alternatives in the choice set should be relevant and feasible and include the attributes considered most by travelers when they choose a route. This research investigated the role and significance of route choice set formations with a focus on the perspectives of the modeler and of travelers. Revealed preference data were collected from Sydney, Australia, residents about their choice of route for their most recent commuting trip. The survey tool was programmed to use the Google Maps application programming interfaces to collect the route choice information, including the selected route and the set of routes that were considered. Three discrete choice models were used to investigate the traveler’s inclination toward certain attributes of routes, considering both car and public ...

Kiran Shakeel

Papers

Measuring users’ satisfaction of the road network using structural equation modeling

Choice Set Formation Behaviour: A Joint Mode and Route Choice Selection Model

Choice Set Formation Behavior: Joint Mode and Route Choice Selection Model:

Incorporating active and non-active mode preferences for Departure time choice behavior

Choice Set Formation Behavior in Selecting Travel Routes: Application of an Interactive Online Survey Platform: