29,986 rated or chosen profiles from 10,066 respondents, in up to 3 tasks of 1 profile varying on 6 attributes.
| Description | UK online panel (n = 10,066 analysed of 10,101) read about one 20-member government committee with randomized composition (women, age, parents, university degree) and three of its decisions (childcare, abortion counselling, menstrual leave), each randomly approved or not; outcomes are rated fairness of the process, agreement with the decision and support for the policy afterwards (1-10). |
|---|---|
| Reference | Reidinger, V., Leemann, L., & Slapin, J. B. (2026). How descriptive over- and under-representation impacts citizens' evaluations of decision-making across policy domains. Political Science Research and Methods. |
| DOI | 10.1017/psrm.2026.10103 |
| Licence | CC0 1.0 |
| Source data | https://doi.org/10.7910/DVN/BCYWJK |
These notes describe the source data, which the IRW reproduces as released. All notes are listed on the Data Notes page.
| Respondents | 10,066 |
|---|---|
| Rows (one per respondent, task and profile) | 29,986 |
| Tasks per respondent (most) | 3 |
| Profiles per task | 1 |
| Attributes | 6 |
| Topic | democracy institutions |
|---|---|
| A profile represents | organisation |
| Country | GB |
| Language shown | en |
| Language of stored levels | en |
| Randomization restrictions | observed in the data (not documented by the source): each respondent sees each of the three policies exactly once (policy drawn without repetition across tasks, six orders); all 54 combinations of the four committee attributes occur |
| Task order | recorded in the deposit |
| Profile position | recorded in the deposit |
Because the attribute levels were not randomized independently, an estimator has to account for the restriction; a plain difference in means across levels can mislead.
Outcomes:
| rating_agree | To what extent do you agree with the decision that the committee made? [rating, 1 (Completely disagree) to 10 (Completely agree)] |
|---|---|
| rating_fair | Do you think that the process by which this decision was made was fair? [rating, 1 (Very unfair) to 10 (Very fair)] |
| rating_support_after | Having seen the decision of the committee, please think again about whether you agree with the following statement: <the policy statement> [rating, 1 (Completely disagree) to 10 (Completely agree)] |
attr_ageattr_decisionattr_parentsattr_policyattr_universityattr_womencov_age_groupcov_attention_pass_1cov_attention_pass_2cov_birth_yearcov_duration_seccov_education_yearscov_gendercov_left_rightcov_parentcov_regioncov_university_degreecov_urban_ruralcov_vote_intentionidprofilerating_agreerating_fairrating_support_aftertasktrial_committee_nametrial_support_before
The layout (one row per respondent, task and profile; choice/rating outcomes; attr_ columns holding each attribute level as displayed) is defined in the IRW conjoint standard. What the outcomes asked is under Design above.
Or load it directly in R or Python (both need a free Redivis account; the first call opens a browser to sign in):
# R
install.packages("remotes")
remotes::install_github("itemresponsewarehouse/Rpkg")
library(irw)
df <- irw_fetch("reidinger_2026_committee_decisions", source = "conj")
# Python
pip install irw
import irw
df = irw.fetch("reidinger_2026_committee_decisions", source="conj")
@article{Reidinger_2026, title={How descriptive over- and under-representation impacts citizens’ evaluations of decision-making across policy domains}, ISSN={2049-8489}, url={http://dx.doi.org/10.1017/psrm.2026.10103}, DOI={10.1017/psrm.2026.10103}, journal={Political Science Research and Methods}, publisher={Cambridge University Press (CUP)}, author={Reidinger, Verena and Leemann, Lucas and Slapin, Jonathan}, year={2026}, month=May, pages={1–20} }
| IRW version | v607 |
|---|---|
| Redivis dataset | irw_conjoint_2 v1.5 |
| Redivis dataset DOI | 10.57761/g2hc-zw49 |
| Manifest pin for this IRW version | v1.4 |
| Metadata source | irw_meta v47.0 |