3,840 rated or chosen profiles from 480 respondents, in up to 8 tasks of 1 profile varying on 6 attributes.
| Description | 480 German recruiters (firms that had received one of the authors' field-experiment applications, 2022) each rated 8 fictitious apprenticeship applicants presented as application documents, varying gender, Turkish vs German name, education, field of study, parental SES and school grades; outcomes are a 0-100% invitation likelihood and a final yes/no invitation per applicant. |
|---|---|
| Reference | Forster, A. G., & Neugebauer, M. (2024). Factorial survey experiments to predict real-world behavior: A cautionary tale from hiring studies. Sociological Science, 11, 886-906. |
| DOI | 10.15195/v11.a32 |
| Licence | CC BY 4.0 |
| Source data | https://doi.org/10.17605/osf.io/x2tcp |
These notes describe the source data, which the IRW reproduces as released. All notes are listed on the Data Notes page.
| Respondents | 480 |
|---|---|
| Rows (one per respondent, task and profile) | 3,840 |
| Tasks per respondent (most) | 8 |
| Profiles per task | 1 |
| Attributes | 6 |
| Tasks with no profile chosen | 1,562 |
| Topic | labour hiring |
|---|---|
| A profile represents | person |
| Country | DE |
| Language shown | de |
| Language of stored levels | en |
| Randomization restrictions | yes (stated by the source): field of study (Mathematics / German studies) exists only for applicants with Abitur + some college; full factorial of 144 vignettes in 18 D-efficient sets of 8, one set per respondent (fixed blocked design); education shares 1/4 intermediate, 1/4 Abitur, 1/2 some college (two study fields), other attributes uniform |
| 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 | I would like to invite [name] (yes/no) (translated) [choice, opt-out allowed] |
|---|---|
| rating | How likely are you to invite the candidate to the next step of the hiring process? (paraphrase) [rating, 0 (0 percent) to 100 (100 percent)] |
attr_achievementattr_educationattr_ethnicityattr_genderattr_sesattr_study_fieldchoicecov_applicants_typicalcov_occupational_fieldcov_recruiter_responsiblecov_vignette_time_seccov_waveidprofileratingtask
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("forster_2024_hiring_vignettes", source = "conj")
# Python
pip install irw
import irw
df = irw.fetch("forster_2024_hiring_vignettes", source="conj")
@article{Forster_2024, title={Factorial Survey Experiments to Predict Real-World Behavior: A Cautionary Tale from Hiring Studies}, volume={11}, ISSN={2330-6696}, url={http://dx.doi.org/10.15195/v11.a32}, DOI={10.15195/v11.a32}, journal={Sociological Science}, publisher={Society for Sociological Science}, author={Forster, Andrea and Neugebauer, Martin}, year={2024}, pages={886–906} }
| 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 |