×

A Monte Carlo study of design-generating algorithms for the latent class mixed logit model. (English) Zbl 1395.90156

Summary: We compare different procedures which generate \(D_{B}\)-efficient designs for choice-based conjoint analysis using the latent class mixed logit model which captures latent consumer heterogeneity in a flexible way. These procedures are the Coordinate-Exchange algorithm, the Relabel-Swap-Cycle algorithm, and the remaining six combinations of the individual components of the latter. Halton draws and a minimum potential design for prior draws both of which reduce computation times serve to determine \(D_{B}\)-errors of designs. We simulate choices for each set of generated designs and constellations which differ with respect to number of choice sets, number of clusters, within cluster heterogeneity, amount of stochastic error, relative cluster size and cluster similarity. Using these artificial choices we estimate parameters of the latent class mixed logit model in the next step. Designs are evaluated by TOPSIS scores which combine estimation accuracy and run time. ANOVA with TOPSIS scores as dependent variable shows that Relabel alone yields the best results of all procedures investigated. Coordinate-Exchange, Swap alone and the combination of Relabel and Swap turn out to be second best. Relabel also leads to much lower run times than the other procedures. We recommend to use Relabel and to avoid Cycle altogether because it performs worst.

MSC:

90B50 Management decision making, including multiple objectives
91B42 Consumer behavior, demand theory
65C05 Monte Carlo methods

Software:

fields; Excel; MADM; rcom
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Andrews, RL; Ansari, A; Currim, IS, Hierarchical Bayes versus finite mixture conjoint analysis models: a comparison of fit, prediction and partworth recovery, J Mark Res, 39, 87-98, (2002) · doi:10.1509/jmkr.39.1.87.18936
[2] Atkinson AC, Donev AN (1992) Optimum experimental designs. Oxford University Press, Clarendon · Zbl 0829.62070
[3] Baier, T; Neuwirth, E, Excel : COM : R, Comput Stat, 22, 91-108, (2007) · Zbl 1186.62002 · doi:10.1007/s00180-007-0023-6
[4] Bhat, CR, Quasi-random maximum simulated likelihood estimation of the mixed multinomial logit model, Transp Res Part B, 35, 677-693, (2001) · doi:10.1016/S0191-2615(00)00014-X
[5] Bliemer, MCJ; Rose, JM, Construction of experimental designs for mixed logit models allowing for correlation across choice observations, Transp Res Part B, 44, 720-734, (2010) · doi:10.1016/j.trb.2009.12.004
[6] Chaloner, K; Verdinelli, I, Bayesian experimental design: a review, Stat Sci, 10, 273-304, (1995) · Zbl 0955.62617 · doi:10.1214/ss/1177009939
[7] Dhar, R; Simonson, I, The effect of forced choice on choice, J Mark Res, 40, 146-160, (2003) · doi:10.1509/jmkr.40.2.146.19229
[8] Evgeniou, T; Pontil, M; Toubia, O, A convex optimization approach to modeling consumer heterogeneity in conjoint estimation, Mark Sci, 26, 805-818, (2007) · doi:10.1287/mksc.1070.0291
[9] Ferrini, S; Scarpa, R, Designs with a-priori information for nonmarket valuation with choice-experiments: a Monte Carlo study, J Environ Econ Manage, 53, 342-363, (2007) · Zbl 1188.91127 · doi:10.1016/j.jeem.2006.10.007
[10] Greene WH (1997) Economic analysis. Prentice Hall, Upper Saddle River
[11] Greene, WH; Hensher, DA, Revealing additional dimensions of preference heterogeneity in a latent class mixed multinomial logit model, Appl Econ, 45, 1897-1902, (2013) · doi:10.1080/00036846.2011.650325
[12] Gustafsson, A; Herrmann, A; Huber, F; Gustafsson, A (ed.); Herrmann, A (ed.); Huber, F (ed.), Conjoint analysis as an instrument of market research practice, 3-30, (2007), Berlin · doi:10.1007/978-3-540-71404-0_1
[13] Huber, J; Zwerina, K, The importance of utility balance in efficient choice designs, J Mark Res, 33, 307-317, (1996) · doi:10.2307/3152127
[14] Kanninen, B, Optimal design for multinomial choice experiments, J Mark Res, 39, 214-222, (2002) · doi:10.1509/jmkr.39.2.214.19080
[15] Kessels R, Goos P, Vandebroek M (2004) Comparing algorithms and criteria for designing Bayesian conjoint choice experiments. DTEW Research Report 0427, pp 1-38
[16] Kessels, R; Goos, P; Vandebroek, M, A comparison of criteria to design efficiency choice experiments, J Mark Res, 43, 409-419, (2006) · doi:10.1509/jmkr.43.3.409
[17] Kessels, R; Jones, B; Goos, P; Vandebroek, M, An efficient algorithm for constructing Bayesian optimal choice designs, J Bus Econ Stat, 27, 279-291, (2009) · doi:10.1198/jbes.2009.0026
[18] McFadden, D; Griliches, Z (ed.); Intriligator, MD (ed.), Econometric analysis of qualitative response models, No. 2, 1395-1457, (1984), New York
[19] McFadden, D; Train, KE, Mixed MNL models for discrete response, J Appl Econ, 15, 447-470, (2000) · doi:10.1002/1099-1255(200009/10)15:5<447::AID-JAE570>3.0.CO;2-1
[20] Nychka D, Furrer R, Paige J, Sain S (2015) Fields: tools for spatial data. R Package Version 9.0. http://CRAN.R-project.org/package=fields. Accessed 9 May 2016
[21] Rose JM, Scarpa R, Bliemer MCJ (2009) Incorporating model uncertainty into the generation of efficient stated choice experiments: a model averaging approach. Working Paper, Institute of Transport and Logistics Studies, University of Sydney
[22] Sándor, Z; Wedel, M, Designing conjoint choice experiments using managers’ prior beliefs, J Mark Res, 38, 430-444, (2001) · doi:10.1509/jmkr.38.4.430.18904
[23] Sándor, Z; Wedel, M, Profile construction in experimental choice designs for mixed logit models, Mark Sci, 21, 455-475, (2002) · doi:10.1287/mksc.21.4.455.131
[24] Scarpa, R; Rose, JM, Design efficiency for non-market valuation with choice modeling: how to measure it, what to report and why, Aust J Agric Resour Econ, 52, 253-282, (2008) · doi:10.1111/j.1467-8489.2007.00436.x
[25] Street, DJ; Burgess, L; Louviere, JJ, Quick and easy choice sets: constructing optimal and nearly optimal stated choice experiments, Int J Res Mark, 22, 459-470, (2005) · doi:10.1016/j.ijresmar.2005.09.003
[26] Toubia, O; Hauser, JR; Simester, DI, Polyhedral methods for adaptive choice-based conjoint analysis, J Mark Res, 41, 116-131, (2004) · doi:10.1509/jmkr.41.1.116.25082
[27] Train KE (2000) Halton sequences for mixed logit. Working Paper, Department of Economics, University of California at Berkeley
[28] Train KE (2003) Discrete choice methods with simulation. Cambridge University Press, New York · Zbl 1047.62098 · doi:10.1017/CBO9780511753930
[29] Train, KE, EM algorithms for nonparametric estimation of mixing distributions, J Choice Model, 1, 40-69, (2008) · doi:10.1016/S1755-5345(13)70022-8
[30] Vermeulen, B; Goos, P; Scarpa, R; Vandebroek, M, Bayesian conjoint choice designs for measuring willingness to pay, Environ Resour Econ, 48, 129-149, (2011) · doi:10.1007/s10640-010-9401-6
[31] Vriens, M; Wedel, M; Wilms, T, Metric conjoint segmentation methods: a Monte Carlo comparison, J Mark Res, 33, 73-85, (1996) · doi:10.2307/3152014
[32] Yoon KP, Hwang C (1995) Multiple attribute decision making: an introduction. SAGE publications, California · doi:10.4135/9781412985161
[33] Yu, J; Goos, P; Vandebroek, M, Efficient conjoint choice designs in the presence of respondent heterogeneity, Mark Sci, 28, 122-135, (2009) · doi:10.1287/mksc.1080.0386
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.