15,992 rated or chosen profiles from 1,999 respondents, in up to 4 tasks of 2 profiles varying on 4 attributes.
| Description | A race-balanced US Qualtrics panel judged pairs of hypothetical neighborhoods described only by racial composition; 1,999 respondents (1,803 after excluding 196 straightliners), 4 pairs each. Outcomes are a forced choice of the more racially diverse neighborhood and a 1-7 diversity rating of each. |
|---|---|
| Reference | Abascal, M., Xu, J., & Baldassarri, D. (2021). People use both heterogeneity and minority representation to evaluate diversity. Science Advances, 7(11), eabf2507. |
| DOI | 10.1126/sciadv.abf2507 |
| Licence | CC0 1.0 |
| Source data | https://doi.org/10.7910/DVN/MTH58P |
These notes describe the source data, which the IRW reproduces as released. All notes are listed on the Data Notes page.
| Respondents | 1,999 |
|---|---|
| Rows (one per respondent, task and profile) | 15,992 |
| Tasks per respondent (most) | 4 |
| Profiles per task | 2 |
| Attributes | 4 |
| Tasks with no profile chosen | 0 |
| Topic | housing neighbourhoods |
|---|---|
| A profile represents | place |
| Country | US |
| Language shown | en |
| Language of stored levels | en |
| Randomization restrictions | yes (stated by the source): the three groups named in a profile are always distinct (largest/second/2% group drawn without repetition from White/Black/Latino/Asian); shares come from 5 fixed patterns |
| 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:
| choice | Which of these two neighborhoods do you think is more racially diverse? [choice, forced] |
|---|---|
| rating | On a scale from 1 to 7, where 1 indicates that the neighborhood is not racially diverse at all and 7 indicates that the neighborhood is very racially diverse, how would you rate this neighborhood? [rating, 1 (not racially diverse at all) to 7 (very racially diverse)] |
attr_largest_groupattr_second_groupattr_sharesattr_third_groupchoicecov_aa_1cov_aa_2cov_aa_3cov_agecov_better_placecov_borncov_educationcov_employmentcov_gendercov_ideologycov_ideology_forcedcov_immigrationcov_incomecov_party_idcov_party_leancov_party_strengthcov_racecov_straightlinercov_vote2016cov_white_advantageidprofileratingtask
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("abascal_2021_neighborhood_diversity", source = "conj")
# Python
pip install irw
import irw
df = irw.fetch("abascal_2021_neighborhood_diversity", source="conj")
@article{Abascal_2021, title={People use both heterogeneity and minority representation to evaluate diversity}, volume={7}, ISSN={2375-2548}, url={http://dx.doi.org/10.1126/sciadv.abf2507}, DOI={10.1126/sciadv.abf2507}, number={11}, journal={Science Advances}, publisher={American Association for the Advancement of Science (AAAS)}, author={Abascal, Maria and Xu, Janet and Baldassarri, Delia}, year={2021}, month=Mar }
| IRW version | v584 |
|---|---|
| Redivis dataset | irw_conjoint v4.2 |
| Redivis dataset DOI | 10.57761/qkye-q530 |
| Manifest pin for this IRW version | v4.2 |
| Metadata source | irw_meta v44.0 |