Nested Logit Model Research Articles

Incorporating Intrahousehold Interactions into a Tour-Based Model of Public Transport Use in Car-Negotiating Households

Intrahousehold interactions in travel are fundamental to an understanding of activity travel behavior, as reflected by the substantial percentage of regional travel that is made jointly. The development of travel demand models that incorporate intrahousehold interactions is crucial to a credible analysis of traveler response to policies. A tour-based modeling framework is used to examine intrahousehold interactions in travel mode choice with a focus on public transport use in households having differences in car availability. An important distinction is made between car-sufficient households (in which there are at least as many cars in the household as license holders) and car-negotiating households (households that have fewer cars than license holders). Intrahousehold interactions and temporal–spatial constraints are explicitly represented by different patterns of joint household tours, with home-based tours as the unit of analysis. The empirical analysis is based on a nested logit model that was developed to integrate intrahousehold interactions with tour-based mode choices; Sydney Household Travel Survey data are used. The results show that joint household travel accounts for more than half of weekday home-based tours in Sydney, Australia. The arrangement of joint household tours is shown to depend on household context, situational factors, and social constraints. Mode choice associated with different joint tour patterns is influenced by household and individual characteristics, tour attributes, and transport-related fringe benefits.

Assessment of Public–Private Partnership in Traveler Information Provision

Making efficient use of transportation infrastructure has always been a concern. Traveler information provisions (TIPs) assist commuters in making better travel decisions and therefore lead to increased mobility and more efficient travel. The ongoing economic crisis and shrinking public funding have made the public–private partnership (PPP) an at tractive instrument for promoting TIP. Such initiatives have been much discussed in developed countries. The use of PPP to fund public projects in developing countries, however, is in its infancy, and the related issues do not receive adequate attention in the literature. In this study, PPP opportunities in TIP were assessed in the case of a city in a developing country, Tehran, Iran. Factors contributing to TIP effectiveness were studied by analyzing commuters’ behavioral changes in response to current radio traffic information. Analysis was conducted with multinomial logit and nested logit models. From this analysis, commuter characteristics, trip purpose, and content of radio traffic information were identified as factors contributing to drivers’ willingness to divert. These findings directed the research to some potential markets and strategies for investment in TIPs. The literature was reviewed to identify some challenges and opportunities of PPP in past experience as well as special regional constraints. On the basis of the modeling results and literature review, business models for PPP in TIPs were outlined. Key findings are that (a) data integration and customization are essential; (b) with respect to purchasing behavior, the market has to be stratified into commuter and corporate markets; and (c) the market for Global Positioning System–based services is promising.

The Regional Location Decision of Foreign Direct Investments in Romania

The regional attraction of foreign direct investments is expected to evolve into an enhancement of local advantages. In this paper we identified the most important benefits which brought the most significant impact on the number of newly established companies with foreign capital at regional level in Romania. Using a nested logit model we described a two stage decision process where the investor first chooses a group of regions with common characteristics, such as the closeness to the capital or to the main transportation routes, and then chooses the specific region from within this group. The main factors of attractiveness are identified in order to be used for stimulating a more equal regional development. Reducing disparities in this way can help to a more advanced economic development of the foreign direct investments’ host country.the paper, comprising about 100 words, should include the purpose and the aims of the paper, methods used, paper structure, basic results, and the conclusion concerning the possible application of the results and the conclusion concerning the possible application of the results.

Exploring Engagement in Household Activities and Decisions on Residential Tenure and Household Type

Residential locations play an important role in the spatial distribution of household activities and travel decisions and, subsequently, in long-term forecasting models. This study examined the relationship between housing location choices, time allocation to out-of-home activities, and other socioeconomic attributes related to household life-cycle stages. A choice model of housing tenure and type was formulated and estimated to provide a methodological framework for examining the impacts of engagement in household activities and life-cycle stage. Engagement in household activities was represented by factor scores from a factor analysis on the proportion of time households spent on 14 activity types. The scores of the identified factors, in addition to other socioeconomic and travel characteristics of the household, were estimated in a nested-logit choice model of housing tenure and type. Furthermore, households were segmented into different life-cycle stages on the basis of household size and age of members. Results from this study revealed that the life-cycle stage of a household had a significant statistical impact on the tenure choice to rent relative to the choice to own a home. In relation to time allocation for household activities, the time allocated to eating, recreation, and social activities was found to have the strongest statistical significance with respect to the choice of tenure and housing type. Overall, estimation results revealed a relationship between the choice of housing tenure and type, attributes of the household, and the allocation of activity time among its members.

A port choice model with logit models: a case study for the Spanish container trade

Earlier research by the authors showed that transport costs, port specific dummy variables and proxies for quality of service aspects have a statistically significant impact on port choice. The objective of this paper is to improve the earlier models through the use of a nested logit model and further by including new variables. The results show that the nested model is an improvement, that the variable indicating the inland transport balance has a statistically significant impact and that the split of variables into distance dependant and independent components gives no improvement. The model outcomes can be used to assess the impact of interventions in ports, and thereby to serve as a basis for the economic and financial evaluation of port projects.

Estimating Nested Logit Models with Censored Data

The presented methodology estimates parameters of a nested logit model when decision makers who choose one of the alternatives are systematically excluded from the sample data that are used to estimate the model (i.e., censored). Unlike existing methods for estimating discrete choice model parameters with censored data, which require exogenous information beyond the specification of the model to be estimated and the available sampled observations, the proposed method requires no additional outside information. It is demonstrated empirically that this approach can recover not only generic model parameters that apply to common attributes of all alternatives but also parameters for alternative-specific constants and variables associated with both observed and censored alternatives. Although the standard errors of the estimated parameters are larger than those of models estimated with uncensored data, censored data methods still hold great potential for applications in which uncensored data are expensive or impossible to collect.

全国貨物流動を対象としたトンキロベースの海運モーダルシフト評価

Modal shift has a lot of merits in environmental and transport safety aspects, but it does not seem that it spreads enough in cargo transportation in Japan. To get effective policies for promoting it, the transportation simulator which can estimate quantitative effect of transportation system change is useful. In this paper, the authors develop cargo flow simulator by using disaggregate nested logit model to analyze changes by effects of policies and economic situation. The simulator the authors develop is a detailed one in which whole country is divided into 207 livelihood spheres, 7x2 patterns of carriage modes are considered and whole inter-domestic cargo flows are treated for each class of articles. It has enough reproducibility, and with the simulator the authors estimate the effect of cargo lot size and modal shift potential besides lead time and transport cost on ton-kilo basis to get basic guiding principles for achieving further modal shift.

混在する“多様な施設（従来店）”と“画一的な施設（コンビニ）”の競合モデル

This paper clarifies the competitive structure of traditional retail stores, where sales of goods are characterized, and retail chains such as convenient stores, where goods are assorted but are standardized, by applying a mathematical model. In general, convenient stores have better drawing power for its efficiency. However, traditional ones become more effective in locations where convenient stores are aggregated and attract consumers with their diversity. Therefore, this paper formulates the complexity of traditional versus convenient stores by utilizing the Nested Logit Model and creates a model to show transformation processes, then, examines numerically and analytically the behaviors of the model.

SEARCH STRATEGY FOR NESTED LOGIT TREE STRUCTURE: A CASE STUDY OF RURAL FEEDER SERVICE TO BUS STOP

Several approaches have been suggested by researchers for identifying the best feasible tree structure for Nested Logit (NL) model. This paper demonstrates an experience of applying those approaches while identifying the best feasible tree structure for NL model with reference to a case study of feeder service to bus stops in rural India. Heteroscedastic Extreme Value (HEV) model, fully degenerated tree structure NL (DGNL) model and several nested logit models based on natural partition principle were developed and analyzed for identifying the most optimal NL model. The results presented in the paper are case specific, but the experiences documented could be useful for selecting the optimal tree structure for NL model in other cases.

Overloaded Vehicle Choice Behavior Analysis Based on Nested Logit Model

To effectively control the overloaded transportation, the trip choice behavior of the overloaded vehicle should be deeply examined. A overloaded vehicle usually makes a series of decisions according to the overloaded level, trip line, etc., to get the maximized economic benefit. Different trip decisions often generate different trip cost of overloaded vehicles and trip benefit. Based on the study of decision behavior and trip utility of carriers who use overloaded vehicles to travel, the nested Logit model is developed considering the hierarchical relationship between the degree of road overloaded vehicles and the trip route for the carriers travel. Based on the probability and quantitative method, the trip decision behaviors of those overloaded vehicles are analyzed, which offers scientific references for the management of overloaded vehicles and the theories of compensation rate of pricing.

Study of Travel Mode Choice Behavior Based on Nested Logit Model

Not only multinomial logit (ML) model is usually used in the analysis of travel mode split, but also nested logit (NL) with the method of phased estimation is used. NL model was developed in the paper which used the simultaneous estimation method to analyze travel mode choice behavior on the basis of the basic theory of disaggregate model and data of stated preference survey (SP). In the course of estimating the parameters, the multi-constrained optimization function in optimal tool of MATLAB was used to solve the maximum likelihood function. Using this method, the parameters of model could be calibrated at the same time. The hit ratios are also accurate. It is found that the NL model approach can consider more factors affecting the travel mode choice of residents, improve the prediction accuracy of model and practicality.

Analysis on Relationship of Mode Choice and Residential Location

The relationship between urban transportation and land use is always an endless main topic in urban planning area. It is based on the theory of Nested Logit model, using the data of daily travel revealed preference survey of Beijing in 2008, set up the integrated model of mode choice and land use in this paper. The model have two levels, the first one is space choice level, which is using the land use variables, such as residential location and mixed land use; the other is mode choice level, taking the transportation variables, like travel time, travel cost etc. Parameter estimation results shown that this kind of model can reflect relevance of mode choice and land use at a more detailed level. It is also indicated that the model precision is high.

Service Area Delimitation of Regional Highway Passenger Transport Hub Using Random-Utility-Based Weighted Voronoi Diagram

This study introduces random utility theory to ordinary weighted Voronoi diagram and describes its application in delimiting the services area of a regional highway passenger transport hub. The Euclidean distance was replaced by a utility function of hub’s capacity factor, travel distance, travel time, and monetary travel cost from passenger’s initial origin to the alternative hubs. The service area was delimited based on utility maximization principle and a nested-logit model for transport hub and travel mode. The application shows that the service area of a hub is not consistent with its administrative boundary. It proves Voronoi diagram is a reasonable and practical tool for detecting the service boundary of a hub by offering an integrated angle to recognize the interacting relationship between hub location, transport network, and passenger’s choice behaviors.

Modeling school bus seat belt usage: Nested and mixed logit approaches

School bus seat belt usage has been of great interest to the school transportation community. Understanding factors that influence students’ decisions about wearing seat belts or not is important in determining the most cost-effective ways to improve belt usage rate, and thus the seat belt safety benefits. This paper presents a rigorous empirical analysis on data from Alabama School Bus Pilot Project using discrete choice modeling framework. In order to collect relevant information on individual student-trips, a new data collection protocol is adopted. Three choice alternatives are considered in the study: wearing, not wearing, and improperly wearing seat belts. A student's choice probabilities of these alternatives are modeled as functions of the student's characteristics and trip attributes. The coefficients of the variables in the functions are estimated first using standard multinomial logit model. Moreover, to account for potential correlations among the three choice alternatives and individual-level preference and response heterogeneity among users, nested and mixed logit models are employed in the investigation. Eight significant influence factors are identified by the final models. Their relative impacts are also quantified. The factors include age, gender and the home county of a student, a student's trip length, time of day, seat location, presence and active involvement of bus aide, and two levels of bus driver involvement. The impact of the seat location on students’ seat belt usage is revealed for the first time by this study. Both hypotheses that some of the choice alternatives are correlated and that individual-level heterogeneity exists are tested statistically significant. In view of this, the nested and the mixed logit model are recommended over the standard multinomial logit model to describe and predict students’ seat belt usage behaviors. The final nested logit model uncovers a correlation between improper wearing and not wearing, indicating there are some unknown or unobserved contributing factors that are common to these two choices. In the final random-parameter mixed logit model, individual preference heterogeneity is captured by random coefficients of county variables. Individual response heterogeneity is reflected in the random effect of a driver's remarks on students’ seat belt usage. Both recommended models are helpful in predicting seat belt usage rate quantitatively for given circumstances, and will provide valuable insights in practice of school transportation management.

대도시권 대중교통 사각지대 통행자들의 수단선택 모형 개발 - 급행버스 노선 도입에 따른 선호의식 조사를 중심으로 -

본 연구는 부산, 대구, 광주, 대전 등 4개 대도시권역을 대상으로 대중교통서비스가 열악한 대중교통사각지역을 선정한 후 이들 지역간을 운행하는 새로운 급행대중교통수단 도입 시 기성 시가지내 통행자들과 수단선택 행태가 어떻게 다른지를 분석하기위해 SP 조사(stated preference survey)를 통한 수단선택 행태변화에 대해 네스티드 로짓모형을 구축하여 분석하였다. 연구결과 대중교통사각지대는 잠재 대중교통수요가 많아 기성시가지에 비해 자가용통행으로부터 새로운 대중교통수단으로 전환하는 통행전환 비율이 매우 높은 것으로 분석되었다. 이러한 연구결과는 향후 대도시권 외곽 순환도로 혹은 외곽지역에서 도심지역으로 연결되는 간선도로를 활용한 새로운 급행 대중교통체계 도입시 수요변화 평가와 외곽지역의 대중교통 잠재수요 분석에도 활용될 수 있을 것으로 판단된다. This study selected blind spot areas for public transportation in four metropolitan cities including Busan, Daegue, Gwangju, and Daejeon. Then this study developed a nested logit model and analyzed the changes of mode choice behaviors after adopting rapid transit system using stated preference(SP) survey. As the study results, blind spot areas have more potential public transportation demand and tendency to shift to public transportation from autos than built-up areas. This study results can be utilized to evaluate demand changes for new rapid transit system in a circular expressway and an arterial highway connecting CBD and surrounding areas. The study results also can be utilized to analyze the potential public transportation demand in the surrounding areas.

Does residential parking supply affect household car ownership? The case of New York City

This paper investigates the impact of residential parking supply on private car ownership, the relationship at the heart of the debate on whether residential parking regulations could be used as a demand management strategy to influence travel behavior. However, no empirical studies have sufficiently answered the question. Many believe that parking has little or no effect on car ownership, while others disagree. The paper analyzes 770 households randomly selected from a household travel survey in the New York City region, and measures their complete parking supply, including garage size, driveway spaces, and on-street parking availability, using Google Streetviews and Bing Maps. Results from a nested logit model show that parking supply can significantly determine household car ownership decisions, even after controlling for the endogeneity between the two. Their influence actually outperforms household income and demographic characteristics, the often-assumed dominant determinants of car ownership. Different parking types also behave differently: driveway spaces are more important to car ownership than garages probably because many residents in the study region do not use a garage for car storage. On-street parking is also important to households with off-street parking. Implications for residential parking policies like the maximum off-street parking standard, resident parking permit, and street cleaning are also discussed.

Angler Heterogeneity and the Species-Specific Demand for Marine Recreational Fishing

Abstract In this study we assess the ability of the Marine Recreational Fishery Statistics Survey (MRFSS) to support single-species recreation demand models. We use the 2000 MRFSS southeast intercept data combined with the economic add-on. We determine that the MRFSS data will support only a few species-specific recreation demand models. Considering species of management interest in the Southeast, we focus on dolphinfish, king mackerel, red snapper, and red drum. We examine single-species recreational fishing behavior using random utility models of demand. We explore mixed logit (i.e., random parameter logit) and finite mixture (i.e., latent class logit) models for dealing with angler heterogeneity. We compare these to the commonly used conditional and nested logit models in terms of the value of catching (and keeping) one additional fish. Mixed logit models illustrate that the value of catch can be highly heterogeneous and, in some cases, can include both positive and negative values. The finite mixture ...

Valuing the environment in developing countries: modelling the impact of distrust in public authorities' ability to deliver public services on the citizens' willingness to pay for improved environmental quality

In this paper, we employ the choice experiment method to estimate citizens' valuation of an intervention that proposes to improve the quality of the wastewater deposited in the Ganges River, India. We interviewed 150 randomly selected citizens of Chandernagore, along the banks of the Ganges River, to elicit their willingness to pay (WTP) for this intervention, measured in terms of higher municipality taxes. The findings reveal that almost all of the citizens value wastewater quality, though majority protested the intervention, and stated that they donot trust the authorities for effective management of funds. These protest responses were controlled for with the nested logit model. The results reveal that the citizens are willing to pay significant amounts for improved wastewater quality. Municipalities could rely to some extent on their citizens' WTP higher taxes but municipalities' performance, trustworthiness, accountability, as well as the citizens' perceptions of these, should be improved.

Spontaneous selection: The influence of product and retailing factors on consumer impulse purchases

Our research examines the effect of product characteristics and retailing factors on the likelihood a consumer makes an impulse purchase. We present a framework for understanding the impulse buying process and use it to explain our findings. Our nested logit model uses data from an adult panel of grocery shoppers over three major household grocery shopping trips. The results indicate that product characteristics have a fifty percent greater influence on impulse buying than do retailing factors. Of the three product characteristics investigated, the hedonic nature of the product has the greatest influence on impulse buying. Of the three retail factors, a store environment with a high–low pricing strategy influences impulse buying the most. Our findings suggest that retailers who want to encourage impulse buying behavior utilize promotional activities and merchandising tactics that attract consumers' attention to emotionally appealing products.

Household-Level Model for Hurricane Evacuation Destination Type Choice Using Hurricane Ivan Data

Hurricanes are costly natural disasters periodically faced by households in coastal and, to some extent, inland areas. Public agencies must understand household behavior to develop evacuation plans that align with evacuee choices and behavior. This paper presents a previously unknown household-level hurricane evacuation destination type choice model. The discrete choice of destination type is modeled using a nested logit model. Although previous literature considers only houses of friends and relatives and hotels for modeling purposes, this paper incorporates public shelters, churches, and an aggregated destination type denoted other. This research found that the variables influencing this choice include hurricane position at evacuation time, household geographic location, race, income, preparation time, changes in evacuation plans, previous experiences with major hurricanes, household members working during the evacuation, and evacuation notices. The findings of this paper are useful to understand the competition among destination types and how the characteristics of the demand can be used to develop evacuation strategies, such as increasing and/or decreasing use of public shelters, and measuring the effect of evacuation notices in areas with high accessibility to hotels.