Integrating psychometric indicators in latent class choice models

Hurtubia, Ricardo; Nguyen, My Hang; Glerum, Aurélie; Bierlaire, Michel

doi:10.1016/j.tra.2014.03.010

Cited by 41 publications

(23 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We construct the class assignment probability as a function of a subset of the latent variables z * 2n (cf. Hurtubia et al, 2014), following a multinomial distribution with probabilities…”

Section: Identification Of Latent Variablesmentioning

confidence: 99%

See 1 more Smart Citation

A hybrid-choice latent-class model for the analysis of the effects of weather on cycling demand

Motoaki

Daziano

2015

Transportation Research Part A: Policy and Practice

View full text Add to dashboard Cite

In this paper we analyze demand for cycling using a discrete choice model with latent variables and a discrete heterogeneity distribution for the taste parameters. More specifically, we use a hybrid choice model where latent variables not only enter into utility but also inform assignment to latent classes. Using a discrete choice experiment we analyze the effects of weather (temperature, rain, and snow), cycling time, slope, cycling facilities (bike lanes), and traffic on cycling decisions by members of Cornell University (in an area with cold and snowy winters and hilly topography). We show that cyclists can be separated into two segments based on a latent factor that summarizes cycling skills and experience. Specifically, cyclists with more skills and experience are less affected by adverse weather conditions. By deriving the median of the ratio of the marginal rate of substitution for the two classes, we show that rain deters cyclists with lower skills from bicycling 2.5 times more strongly than those with better cycling skills. The median effects also show that snow is almost 4 times more deterrent to the class of less experienced cyclists. We also model the effect of external restrictions (accidents, crime, mechanical problems) and physical condition as latent factors affecting cycling choices.

show abstract

“…We construct the class assignment probability as a function of a subset of the latent variables z * 2n (cf. Hurtubia et al, 2014), following a multinomial distribution with probabilities…”

Section: Identification Of Latent Variablesmentioning

confidence: 99%

“…In this work we use a full information estimator for the combination of a hybrid choice model with a latent class module. Our methodological approach differs from the work of Hurtubia et al (2014) in that we model the effect of the latent variables on the class assignment probabilities. The remainder of the paper proceeds as follows.…”

Section: Introductionmentioning

confidence: 99%

A hybrid-choice latent-class model for the analysis of the effects of weather on cycling demand

Motoaki

Daziano

2015

Transportation Research Part A: Policy and Practice

View full text Add to dashboard Cite

show abstract

“…In future applications of this work, attitudinal dimensions could be used in choice modelling to explain and predict travel behaviour (Hess et al 2013;Hurtubia et al 2014;Vredin Johannson et al 2006).…”

Section: Discussionmentioning

confidence: 98%

Gauging interventions for sustainable travel: A comparative study of travel attitudes in Berlin and London

Kandt

Rode

Hoffmann

et al. 2015

Transportation Research Part A: Policy and Practice

View full text Add to dashboard Cite

So-called 'soft' policy instruments that respond to the psychological aspects of travel are regularly acknowledged as necessary complements to 'hard' infrastructure investments to effectively promote sustainable travel in cities. While studies investigating subjective orientations among travellers have proliferated, open questions remain including the role of recent technological advances, the expansion of alternative mobility services, locally specific mobility cultures and residential selection. This paper presents the methods, results and policy implications of a comparative study aiming to understand mobility attitudes and behaviours in the wider metropolitan regions of Berlin and London. We specifically considered information and communication technology (ICT), new types of mobility services such as car sharing, electric cars and residential preferences. In each region, we identified six comparable segments with distinct attitudinal profiles, socio-demographic properties and behavioural patterns. Geocoding of the home address of respondents further revealed varying contextual opportunities and constraints that are likely to influence travel attitudes. We find that there is significant potential for uptake of sustainable travel practices in both metropolitan regions, if policy interventions are designed and targeted in accordance with group-specific needs and preferences and respond to local conditions of mobility culture. We identify such interventions for each segment and 2 region and conclude that comparative assessment of attitudinal, alongside geographical, characteristics of metropolitan travellers can provide better strategic input for realistic scenario-building and ex-ante assessment of sustainable transport policy. KeywordsTravel attitudes, travel behaviour, cluster analysis, comparative study, transport policy Highlights  We segment travellers into attitudinal types based on travel and related attitudes. We consider ICT, car sharing, electric cars and residential choices. Six attitudinal segments that are comparable across Berlin and London emerge. The segments differ in potential uptake of sustainable modes and mobility services. Segment-specific interventions to promote sustainable travel are proposed.3

show abstract

“…This approach (Hurtubia et al, 2014) does not attempt to categorize continuous latent variables per se, but rather to include psychometric indicators into a latent class framework. In this structure, it is assumed that the latent variable depends exclusively on positively observed characteristics of the individuals (X) 4 , while its error term follows a Logistic distribution with zero mean and scale parameter λ (which has to be fixed without loss of generality).…”

Section: B) Latent Class With Psychometric Indicators Approach (Lcpi)mentioning

confidence: 99%

“…In the LCPI classes are defined exclusively to maximize the goodness-of-fit and are not based on theoretical assumptions (additionally, the measurement equations would have more degrees-of-freedom). As a matter of fact, if we consider the likelihood of the discrete choice component only, it is clear that a simple latent class model (with no indicators) would outperform every competing approach (including the LCPI; Hurtubia et al, 2014), as in this case the latent classes do not have to satisfy, additionally, a distribution of indicators or theoretical assumptions.…”

Section: Case Studiesmentioning

confidence: 99%

About the Categorization of Latent Variables in Hybrid Choice Models

Bahamonde-Birke

Ortúzar

2015

SSRN Journal

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. is not possibly to assign an individual to a specific group, but only to establish a probability with which an individual should be categorized in given way. Terms of use: Documents inIn this paper we explore different ways to categorize individuals based on latent characteristics, focusing on the categorization of latent variables. This approach exhibits as main advantage (over latent-classes for instance) a clear interpretation of the function utilized in the categorization process, as well as taking exogenous information into account. Unfortunately, technical issues (associated with the estimation technique via simulation) arise when attempting a direct categorization. analysis, we conclude that the direct categorization is the superior approach, as it offers a consistent treatment of the error term, in accordance with underlying theories, and a better goodness-of-fit.

show abstract

Integrating psychometric indicators in latent class choice models

Cited by 41 publications

References 25 publications

A hybrid-choice latent-class model for the analysis of the effects of weather on cycling demand

A hybrid-choice latent-class model for the analysis of the effects of weather on cycling demand

Gauging interventions for sustainable travel: A comparative study of travel attitudes in Berlin and London

About the Categorization of Latent Variables in Hybrid Choice Models

Contact Info

Product

Resources

About