Abstract
Discrete choice experiments have proven useful in areas such as marketing, government planning, medical studies and psychological research, to help understand consumer preferences. To aid in these experiments, several groups of authors have contributed to the theoretical development of D-optimal and A-optimal discrete choice designs under the multinomial logit (MNL) model. In the setting in which the class of feasible designs is too large for complete search, Sun and Dean (J Stat Plann Inference 170:144–157, 2016) proposed a construction method for A-optimal designs for estimating a set of orthonormal contrasts in the option utilities via a linearization of the MNL model. In this paper, we show that the set of A-optimal designs that result from this linearization may or may not include the optimal design under the MNL model itself. We provide an alternative linearization that leads to an information matrix which coincides with that under the MNL model and, consequently, selects the same set of designs as being A-optimal. We obtain a bound for the average variance of a set of contrasts of interest under the MNL model, and show that the construction method of Sun and Dean (2016) can be used to identify A-optimal and A-efficient designs under the MNL model for both equal and unequal utilities.
Similar content being viewed by others
References
Atkinson A, Donev A, Tobias R (2007) Optimum experimental designs, with SAS. Oxford University Press, Oxford
Atkinson AC, Fedorov VV, Herzberg AM, Zhang R (2014) Elemental information matrices and optimal experimental design for generalized regression models. J Stat Plann Inference 144:81–91
Croissant Yves (2019) Package “mlogit”. https://cran.r-project.org/web/packages/mlogit/
Das A, Singh R (2020) A unified approach to discrete choice experiments. J Stat Plann Inference 205:193–202
El-Helbawy AT, Bradley RA (1978) Treatment contrasts in paired comparisons: large-sample results, applications, and some optimal designs. J Am Stat Assoc 73(364):831–839
Fahrmeir L, Kaufmann H (1985) Consistency and asymptotic normality of the maximum likelihood estimator in generalized linear models. Ann Stat 13(1):342–368
Graßhoff U, Großmann H, Holling H, Schwabe R (2004) Optimal designs for main effects in linear paired comparison models. J Stat Plann Inference 126(1):361–376
Graßhoff U, Großmann H, Holling H, Schwabe R (2013) Optimal design for discrete choice experiments. J Stat Plann Inference 143(1):167–175
Graßhoff U, Schwabe R (2008) Optimal design for the Bradley–Terry paired comparison model. Stat Methods Appl 17(3):275–289
Großmann H, Schwabe R (2015) Design for discrete choice experiments. In: Dean A, Morris M, Stufken J, Bingham D (eds) Handbook of design and analysis of experiments. Chapman and Hall/CRC, Boca Raton, pp 787–831
Großmann H, Holling H, Schwabe R (2002) Advances in optimum experimental design for conjoint analysis and discrete choice models. In: Franses PH, Montgomery AL (eds) Econometric models in marketing. Advances in Econometrics, vol 16. JAI Press INC., Amsterdam, pp 93–118
Huber J, Zwerina K (1996) The importance of utility balance in efficient choice designs. J Mark Res 33:307–317
Jaynes J, Wong WK, Xu H (2016) Using blocked fractional factorial designs to construct discrete choice experiments for healthcare studies. Stat Med 35(15):2543–2560
Jaynes J, Xu H, Wong WK (2017) Minimum aberration designs for discrete choice experiments. J Stat Theory Pract 11(2):339–360
Kessels R, Jones B, Goos P, Vandebroek M (2009) An efficient algorithm for constructing Bayesian optimal choice designs. J Bus Econ Stat 27:279–291
Khuri AI (2009) Linear model methodology. Chapman and Hall/CRC, London
Kuhfeld W (2005) Marketing research methods in SAS: experimental design, efficiency, coding and choice designs. SAS Institute Inc, Cary
Kuhfeld WF (2010) Marketing research methods in SAS: experimental design, choice, conjoint, and graphical techniques. In SAS Document TS-694. http://support.sas.com/techsup/technote/mr2010.pdf. Accessed Feb 2020
McFadden D (1974) Conditional logit analysis of qualitative choice behavior. In: Zarembka P (ed) Frontiers in econometrics. Academic Press, New York, pp 105–142
R Core Team (2017) R: a language and environment for statistical computing. https://www.R-project.org/
Ruan S, MacEachern SN, Otter T, Dean AM (2008) The dependent Poisson race model and modeling dependence in conjoint choice experiments. Psychometrika 73(2):261–288
Sándor Z, Wedel M (2001) Designing conjoint choice experiments using managers’ prior beliefs. J Mark Res 38:430–444
Street DJ, Burgess L (2007) The construction of optimal stated choice experiments: theory and methods. Wiley, Hoboken
Street DJ, Burgess L (2012) Designs for choice experiments for the multinomial logit model. In: Hinkelmann K (ed) Design and analysis of experiments, special designs and applications, vol 3. Wiley, Hoboken, pp 331–378
Sun F, Dean A (2016) \({A}\)-optimal and \({A}\)-efficient designs for discrete choice experiments. J Stat Plann Inference 170:144–157
Sun F, Dean A (2017) A-efficient discrete choice designs for attributes with unequal numbers of levels. J Stat Theory Pract 11(2):322–338
Train KE (2009) Discrete choice methods with simulation. Cambridge University Press, Cambridge
Acknowledgements
The authors would like to thank the reviewers for their extremely helpful comments that have helped considerably in improving the paper. Part of this work was done when Rakhi Singh was a postdoc at TU Dortmund and she was then supported by the Deutsche Forschungsgemeinschaft (SFB 823, Teilprojekt C2). Ashish Das’s work was supported by the Science and Engineering Research Board, India (SR/S4/MS: 829/12).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
Proof of Lemma 1
For the ith choice set, let \(\varDelta _i\) be an \(L\times m\) index matrix with 1 in column j, row w, if the jth option in \(C_i\) is option w, i.e. if \(t_{i_j}\in C_i\) is \(t_{w}\in T\). Then using the definition of \(F_{i}\), \(F_{i_j}\) and \(f_{i_j,i_k}\) in Sect. 3.1 and \(Z_i\) and \(D_i\) in (9), it follows that
Therefore,
From (9),
The result follows since \(Z=[Z_1^{\top }, \ldots , Z^{\top }_N]^{\top }\) and \(F^{\top }=[F_1, \ldots , F_N]^{\top }\). \(\square \)
Rights and permissions
About this article
Cite this article
Singh, R., Dean, A., Das, A. et al. A-optimal designs under a linearized model for discrete choice experiments. Metrika 84, 445–465 (2021). https://doi.org/10.1007/s00184-020-00771-5
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00184-020-00771-5