25,030 rated or chosen profiles from 2,503 respondents, in up to 5 tasks of 2 profiles varying on 7 attributes.
One of 2 tables from the same source; this one is the pairs table. The others are listed under Related tables.
| Description | 2,503 US adults (quota online sample, 2021) compared five pairs of hypothetical US congressional candidates described by ethnicity, career, gender, incumbency, prior elected office, party and political views; they chose one candidate or 'no preference'. |
|---|---|
| Reference | Lublin, D., & Wright, M. (2023). Diversity matters: The election of Asian Americans to U.S. state and federal legislatures. American Political Science Review. |
| DOI | 10.1017/s0003055423000242 |
| Licence | CC0 1.0 |
| Source data | https://doi.org/10.7910/dvn/nyoxte |
These notes describe the source data, which the IRW reproduces as released. All notes are listed on the Data Notes page.
| Respondents | 2,503 |
|---|---|
| Rows (one per respondent, task and profile) | 25,030 |
| Tasks per respondent (most) | 5 |
| Profiles per task | 2 |
| Attributes | 7 |
| Tasks with no profile chosen | 1,959 |
| Topic | candidate choice |
|---|---|
| A profile represents | person |
| Country | US |
| Language shown | en |
| Language of stored levels | en |
| Randomization restrictions | yes (stated by the source): observed: every pair has one Democrat and one Republican and one incumbent and one challenger; political views never pair Liberal-Liberal or Conservative-Conservative; ethnicity is drawn conditionally on the respondent's group (as in the vignette), so level shares depend on the respondent |
| Task order | recorded in the deposit |
| Profile position | inferred from row order |
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. Task order or profile position was rebuilt from row order; analyses of position or task order should leave it out.
Outcomes:
| choice | Now, imagine that the two candidates below are running against each other ... (paraphrase; truncated variable label QCANDPREFA) [choice, opt-out allowed] |
|---|
attr_careerattr_ethnicityattr_genderattr_incumbencyattr_partyattr_political_viewsattr_prior_elected_officechoicecov_agecov_asian_origincov_educationcov_gendercov_party_id7cov_respondent_ethnicityidprofiletask
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("lublin_2023_candidate_pairs", source = "conj")
# Python
pip install irw
import irw
df = irw.fetch("lublin_2023_candidate_pairs", source="conj")
@article{LUBLIN_2023, title={Diversity Matters: The Election of Asian Americans to U.S. State and Federal Legislatures}, volume={118}, ISSN={1537-5943}, url={http://dx.doi.org/10.1017/s0003055423000242}, DOI={10.1017/s0003055423000242}, number={1}, journal={American Political Science Review}, publisher={Cambridge University Press (CUP)}, author={LUBLIN, DAVID and WRIGHT, MATTHEW}, year={2023}, month=Mar, pages={380–400} }
| IRW version | v584 |
|---|---|
| Redivis dataset | irw_conjoint_2 v1.4 |
| Redivis dataset DOI | 10.57761/hk97-wv30 |
| Manifest pin for this IRW version | v1.4 |
| Metadata source | irw_meta v44.0 |