Conjoint Experiments

Research on Conjoint Experiments

Our research explores various aspects of conjoint experiments, including methods to analyze conjoint data and studies examining different facets of conjoint design.

Introduction to Conjoint

In Bansak et al. (2021), we provide an accessible introduction to the design and analysis of conjoint experiments.

Average Marginal Component Effects (AMCEs)

Average Marginal Component Effects (AMCEs) allow researchers to non-parametrically identify and estimate the effects of profile attributes on outcomes (e.g., respondent rankings or ratings). The method is based on the approaches developed in Hainmueller, Hopkins, and Yamamoto (2014). Researchers can implement these methods using the scripts linked below or the cjoint package in R.

In Bansak et al. (2023), we demonstrate how AMCEs can be applied to analyze electoral conjoints specifically.

Resources:

Conjoint Design

Our research also examines various aspects of conjoint design. We have also developed the Conjoint Survey Design Tool to enable researchers to implement conjoint surveys in Qualtrics.

Conjoint Survey Design Tool

Key Areas of Study:

External validity of conjoints: Hainmueller, Hangartner, and Yamamoto (2015)
Using eye-tracking to examine robustness of conjoint designs: Jenke et al. (2021)
Number of attributes and profiles: Bansak et al. (2021)
Number of choice tasks: Bansak et al. (2018)

References

Book Chapters

Book Chapter

Conjoint Survey Experiments

Kirk Bansak, Jens Hainmueller, Daniel J. Hopkins, and Teppei Yamamoto

In Advances in Experimental Political Science, 2021

Bib PDF

@incollection{Bansak_Hainmueller_Hopkins_Yamamoto_2021,
  place = {Cambridge},
  title = {Conjoint Survey Experiments},
  booktitle = {Advances in Experimental Political Science},
  publisher = {Cambridge University Press},
  author = {Bansak, Kirk and Hainmueller, Jens and Hopkins, Daniel J. and Yamamoto, Teppei},
  editor = {Druckman, James N. and Green, Donald P.Editors},
  year = {2021},
  pages = {19–41},
}

Journal Articles

Political Analysis

Causal inference in conjoint analysis: Understanding multidimensional choices via stated preference experiments

Jens Hainmueller, Daniel J Hopkins, and Teppei Yamamoto

Political Analysis, 2014

Miller Prize DOI Bib HTML PDF

Miller Prize for best work appearing in Political Analysis the preceding year (https://polmeth.org/miller-prize).

@article{hainmueller2014causal,
  title = {Causal inference in conjoint analysis: Understanding multidimensional choices via stated preference experiments},
  author = {Hainmueller, Jens and Hopkins, Daniel J and Yamamoto, Teppei},
  journal = {Political Analysis},
  volume = {22},
  number = {1},
  pages = {1--30},
  year = {2014},
  publisher = {Cambridge University Press},
  doi = {10.1093/pan/mpt024  },
  url = {https://doi.org/10.1093/pan/mpt024  },
}

Political Analysis

Using conjoint experiments to analyze election outcomes: The essential role of the average marginal component effect

Kirk Bansak, Jens Hainmueller, Daniel J. Hopkins, and Teppei Yamamoto

Political Analysis, 2023

DOI Bib HTML PDF

@article{bansak2023using,
  title = {Using conjoint experiments to analyze election outcomes: The essential role of the average marginal component effect},
  author = {Bansak, Kirk and Hainmueller, Jens and Hopkins, Daniel J. and Yamamoto, Teppei},
  journal = {Political Analysis},
  volume = {31},
  number = {4},
  pages = {500--518},
  year = {2023},
  publisher = {Cambridge University Press},
  doi = {10.1017/pan.2023.19},
  url = {https://doi.org/10.1017/pan.2023.19},
}

PNAS

Validating vignette and conjoint survey experiments against real-world behavior

Jens Hainmueller, Dominik Hangartner, and Teppei Yamamoto

Proceedings of the National Academy of Sciences, 2015

DOI Bib HTML PDF

@article{hainmueller2015validating,
  title = {Validating vignette and conjoint survey experiments against real-world behavior},
  author = {Hainmueller, Jens and Hangartner, Dominik and Yamamoto, Teppei},
  journal = {Proceedings of the National Academy of Sciences},
  volume = {112},
  number = {8},
  pages = {2395--2400},
  year = {2015},
  publisher = {National Acad Sciences},
  doi = { 10.1073/pnas.141658711 },
  url = {  https://doi.org/10.1073/pnas.141658711},
}

Political Analysis

Using eye-tracking to understand decision-making in conjoint experiments

Lucas Jenke, Kirk Bansak, Jens Hainmueller, and Dominik Hangartner

Political Analysis, 2021

DOI Bib HTML PDF

@article{jenke2021eyetracking,
  title = {Using eye-tracking to understand decision-making in conjoint experiments},
  author = {Jenke, Lucas and Bansak, Kirk and Hainmueller, Jens and Hangartner, Dominik},
  journal = {Political Analysis},
  volume = {29},
  number = {1},
  pages = {75--101},
  year = {2021},
  publisher = {Cambridge University Press},
  doi = {10.1017/pan.2020.14},
  url = {https://doi.org/10.1017/pan.2020.14},
}

PSRM

Beyond the breaking point? Survey satisficing in conjoint experiments

Kirk Bansak, Jens Hainmueller, Daniel J. Hopkins, and Teppei Yamamoto

Political Science Research and Methods, 2021

DOI Bib HTML PDF

@article{bansak2021beyond,
  title = {Beyond the breaking point? Survey satisficing in conjoint experiments},
  author = {Bansak, Kirk and Hainmueller, Jens and Hopkins, Daniel J. and Yamamoto, Teppei},
  journal = {Political Science Research and Methods},
  volume = {9},
  number = {1},
  pages = {53--71},
  year = {2021},
  publisher = {Cambridge University Press},
  doi = {10.1017/psrm.2019.57},
  url = {https://doi.org/10.1017/psrm.2019.57},
}

Political Analysis

The number of choice tasks and survey satisficing in conjoint experiments

Kirk Bansak, Jens Hainmueller, Daniel J. Hopkins, and Teppei Yamamoto

Political Analysis, 2018

DOI Bib HTML PDF

@article{bansak2018number,
  title = {The number of choice tasks and survey satisficing in conjoint experiments},
  author = {Bansak, Kirk and Hainmueller, Jens and Hopkins, Daniel J. and Yamamoto, Teppei},
  journal = {Political Analysis},
  volume = {26},
  number = {1},
  pages = {112--119},
  year = {2018},
  doi = {10.1017/pan.2017.32},
  url = {https://doi.org/10.1017/pan.2017.32},
}