Stated-Choice Design Factors Affecting Probability of Nontrading and Precision of Value-of-Time Estimates: Meta-Analysis of Individual Participant Data
Restricted accessResearch articleFirst published online 2017
Stated-Choice Design Factors Affecting Probability of Nontrading and Precision of Value-of-Time Estimates: Meta-Analysis of Individual Participant Data
The presented approach to stated-choice design takes into account the characteristics of real data, including nontrading responses and their possible effect on value-of-time estimates. A meta-analysis of individual participant data from 51 stated-choice surveys was undertaken to develop models of how characteristics of stated-choice designs affected the proportions of nontraders and the precision of value-of-time estimates. The modeling work confirmed tension between increasing the range of boundary values of time to be tested—reducing nontrading—and reducing the intervals between adjacent boundary values of time—increasing the precision of the value-of-time estimate. An optimization model was developed to find the parameter values for a distribution of boundary values of time that would maximize the expected precision of a value-of-time estimate, given a type of distribution and subject to a series of restrictions. The lognormal distribution was found to work well, and the nonlinear optimization problem could be solved quickly with a standard spreadsheet optimization tool. The optimization model produced a recommended set of boundary values of time that could be used as the starting point for stated-choice designs. The meta-analysis models could also be used to analyze stated-choice designs produced by other means, for instance, as a complement to the use of commercial efficient design software.
Get full access to this article
View all access options for this article.
References
1.
HessS., RoseJ., and PolakJ.. Non-trading, Lexicographic and Inconsistent Behaviour in Stated Choice Data. Transportation Research Part D: Transport and Environment, Vol. 15, No. 7, 2010, pp. 405–417. https://doi.org/10.1016/j.trd.2010.04.008.
HessS., StathopoulosA., and DalyA.. Allowing for Heterogeneous Decision Rules in Discrete Choice Models: An Approach and Four Case Studies. Transportation, Vol. 39, No. 3, 2012, pp. 565–591. https://doi.org/10.1007/s11116-011-9365-6.
5.
BörjessonM., FosgerauM., and AlgersS.. Catching the Tail: Empirical Identification of the Distribution of the Value of Travel Time. Transportation Research Part A: Policy and Practice, Vol. 46, No. 2, 2012, pp. 378–391. https://doi.org/10.1016/j.tra.2011.10.006.
6.
FowkesT., and WardmanM.. The Design of Stated Preference Travel Choice Experiments: With Special Reference to Interpersonal Taste Variations. Journal of Transport Economics and Policy, Vol. 22, No. 1, 1988, pp. 27–44.
7.
FosgerauM., HjorthK., and Lyk-JensenS. V.. Results for Experiment 1. In The Danish Value of Time Study, Final Report. Danish Transport Research Institute, Lyngby, 2007.
8.
RoseJ., HessS., and CollinsA.. What If My Model Assumptions Are Wrong? The Impact of Non-Standard Behaviour on Choice Model Estimation. Journal of Transport Economics and Policy, Vol. 47, No. 2, 2013, pp. 245–263.
9.
KilliM., NossumÅ., and VeistenK.. Lexicographic Answering in Travel Choice: Insufficient Scale Extensions and Steep Indifference Curves. European Journal of Transport and Infrastructure Research, Vol. 7, No. 1, 2007, pp. 39–62.
10.
Van de KaaE. J.Assessment of the Value of Travel Time from Stated-Choice Surveys: The Treatment of Lexicographic Answering. TRAIL Research School, Delft, Netherlands, 2006.
11.
ChorusC.Capturing Alternative Decision Rules in Travel Choice Models: A Critical Discussion. In Handbook of Choice Modelling, Edward Elgar Publishing, Northampton, Mass., 2014, pp. 295–297.
12.
FosgerauM., and BörjessonM.. Manipulating a Stated-Choice Experiment. Journal of Choice Modelling, Vol. 16, 2015, pp. 43–49. https://doi.org/10.1016/j.jocm.2015.09.005.
13.
Ojeda-CabralM., HessS., and BatleyR.. Understanding Valuation of Travel Time Changes: Are Preferences Different Under Different Stated-Choice Design Settings?Transportation, April2016, pp. 1–21.
14.
HessS., StathopoulosA., CampbellD., O’NeillV., and CaussadeS.. It’s Not That I Don’t Care, I Just Don’t Care Very Much: Confounding Between Attribute Non-attendance and Taste Heterogeneity. Transportation, Vol. 40, No. 3, 2013, pp. 583–607. https://doi.org/10.1007/s11116-012-9438-1.
15.
WardmanM., and IbáñezJ.. Testing Contextual and Design Effects on Inter-Urban Motorists’ Responses to Time Savings. Journal of Transport Economics and Policy, Vol. 47, No. 1, 2013, pp. 123–141.
16.
AbrantesP. A. L., and WardmanM. R.. Meta-Analysis of UK Values of Travel Time: An Update. Transportation Research Part A: Policy and Practice, Vol. 45, No. 1, Jan. 2011, pp. 1–17. https://doi.org/10.1016/j.tra.2010.08.003.
17.
WardmanM., ChintakayalaP., de JongG., and FerrerD.. European-wide Meta-Analysis of Values of Travel Time. University of Leeds, West Yorkshire, UK, 2012.
18.
MeyerhoffJ., MørkbakM. R., and OlsenS. B.. A Meta-study Investigating the Sources of Protest Behaviour in Stated Preference Surveys. Environmental and Resource Economics, Vol. 58, No. 1, May2014, pp. 35–57. https://doi.org/10.1007/s10640-013-9688-1.
19.
MitraniA.Empirical Evidence on Ratio of Means Problem and Estimation of Values of Time with Stated Preference Data. Presented at 92nd Annual Meeting of the Transportation Research Board, Washington, D.C., 2013.
20.
AhmedI., SuttonA. J., and RileyR. D.. Assessment of Publication Bias, Selection Bias, and Unavailable Data in Meta-Analyses Using Individual Participant Data: A Database Survey. BMJ, Vol. 344, No. 1, 2012, pp. 1–10.
Gini (Gross Income, Before Taxes). Organisation for Economic Co-operation and Development, Paris. http://stats.oecd.org. Accessed Oct. 26, 2016.
28.
AlmésticaE. V. S.What Happened to the Distribution of Income in Puerto Rico During the Last Three Decades of the XX Century? A Statistical Point of View. http://economia.uprrp.edu/ensayo129.pdf. Accessed Oct. 26, 2016.
29.
BörjessonM., and EliassonJ.. Experiences from the Swedish Value of Time Study. Transportation Research Part A: Policy and Practice, Vol. 59, No. 1, 2012, 2014, pp. 144–158. https://doi.org/10.1016/j.tra.2013.10.022.
30.
RamjerdiF., FlügelS., SamstadH., and KilliM.. Den Norske verdsettingsstudien—Tid: Rapporten uten vedlegg. Norwegian Centre for Transport Research, Oslo, 2010.
31.
RamjerdiF., FlügelS., SamstadH., and KilliM.. Den Norske verdsettingsstudien—Tid: Vedleggene. Norwegian Centre for Transport Research, Oslo, 2010.
32.
Ojeda CabralM., BatleyR., and HessS.. The Value of Travel Time: Random Utility Versus Random Valuation. Transportmetrica A: Transportation Science, Vol. 12, No. 3, 2016, pp. 230–248.
FosgerauM., and BierlaireM.. Discrete Choice Models with Multiplicative Error Terms. Transportation Research Part B: Methodological, Vol. 43, No. 5, 2009, pp. 494–505. https://doi.org/10.1016/j.trb.2008.10.004.
35.
HessS., DalyA., DekkerT., Ojeda-CabralM., and BatleyR.. A Framework for Capturing Heterogeneity, Heteroscedasticity, Non-Linearity, Reference Dependence, and Design Artefacts in Value of Time Research. Transportation Research Part B: Methodological, Vol. 96, 2017, pp. 126–129.
36.
Stata Statistical Software: Release 13. StataCorp, College Station, Tex.
37.
HoleA. R.Fitting Mixed Logit Models by Using Maximum Simulated Likelihood. Stata Journal, Vol. 7, No. 3, 2007, pp. 388–401.
38.
BierlaireM.BIOGEME: A Free Package for the Estimation of Discrete Choice Models. Presented at 3rd Swiss Transport Research Conference, Ascona, 2003.
39.
DumontJ., HessS., and DalyA.. Are Nontraders the Achilles Heel of the Mixed Logit Model?Presented at 92nd Annual Meeting of the Transportation Research Board, Washington, D.C., 2013.
FylstraD., LasdonL., WatsonJ., and WarenA.. Design and Use of the Microsoft Excel Solver: Interfaces. Interfaces, Vol. 28, No. 5, 1998, pp. 29–55. https://doi.org/10.1287/inte.28.5.29.
