2,028 rated or chosen profiles from 2,028 respondents, in up to 1 tasks of 1 profile varying on 2 attributes.
| Description | 2,028 US adults each watched one video of a crime in progress in which the offenders' race (Black or White) and the victim's race (Black or White) were randomized, then rated how likely they would be to call the police, find witnesses, take a picture, follow, confront or detain the offenders, and how unsafe physical intervention would be. |
|---|---|
| Reference | Barnum, T. C., Herman, S., Nagin, D. S., & Pickett, J. T. (2026). Understanding bystander decision-making: Experimental evidence on when and how people respond to crime. Criminology. |
| DOI | 10.1111/1745-9125.70048 |
| Licence | CC0 1.0 |
| Source data | https://doi.org/10.7910/dvn/ffliht |
These notes describe the source data, which the IRW reproduces as released. All notes are listed on the Data Notes page.
| Respondents | 2,028 |
|---|---|
| Rows (one per respondent, task and profile) | 2,028 |
| Tasks per respondent (most) | 1 |
| Profiles per task | 1 |
| Attributes | 2 |
| Topic | crime justice policing |
|---|---|
| A profile represents | scenario |
| Country | US |
| Language shown | en |
| Language of stored levels | en |
| Randomization restrictions | unknown |
| Task order | inferred from row order |
| Profile position | inferred from row order |
Task order or profile position was rebuilt from row order; analyses of position or task order should leave it out.
Outcomes:
| rating_call_police | If you saw this crime happen, how likely or unlikely is it that YOU would do each of the following: call the police? (paraphrase; item text truncated in the deposit, item identified by the authors' variable names) [rating, 1 (Very likely) to 5 (Very unlikely)] |
|---|---|
| rating_confront_offender | If you saw this crime happen, how likely or unlikely is it that YOU would do each of the following: confront the offender(s)? (paraphrase; item text truncated in the deposit, item identified by the authors' variable names) [rating, 1 (Very likely) to 5 (Very unlikely)] |
| rating_detain_offender | If you saw this crime happen, how likely or unlikely is it that YOU would do each of the following: detain the offender(s)? (paraphrase; item text truncated in the deposit, item identified by the authors' variable names) [rating, 1 (Very likely) to 5 (Very unlikely)] |
| rating_find_witnesses | If you saw this crime happen, how likely or unlikely is it that YOU would do each of the following: find witnesses? (paraphrase; item text truncated in the deposit, item identified by the authors' variable names) [rating, 1 (Very likely) to 5 (Very unlikely)] |
| rating_follow_offender | If you saw this crime happen, how likely or unlikely is it that YOU would do each of the following: follow the offender(s)? (paraphrase; item text truncated in the deposit, item identified by the authors' variable names) [rating, 1 (Very likely) to 5 (Very unlikely)] |
| rating_take_picture | If you saw this crime happen, how likely or unlikely is it that YOU would do each of the following: take a picture? (paraphrase; item text truncated in the deposit, item identified by the authors' variable names) [rating, 1 (Very likely) to 5 (Very unlikely)] |
| rating_unsafe_to_intervene | Thinking again about the incident you just witnessed: how safe or unsafe do you [think physical intervention would be]? (paraphrase; label truncated in the deposit) [rating, 1 (Very safe) to 5 (Very unsafe)] |
attr_offender_raceattr_victim_racecov_birth_yearcov_educationcov_gendercov_hispaniccov_raceidprofilerating_call_policerating_confront_offenderrating_detain_offenderrating_find_witnessesrating_follow_offenderrating_take_picturerating_unsafe_to_intervenetask
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("barnum_2026_bystander_video", source = "conj")
# Python
pip install irw
import irw
df = irw.fetch("barnum_2026_bystander_video", source="conj")
@article{Barnum_2026, title={Understanding bystander decision‐making: Experimental evidence on when and how people respond to crime}, ISSN={1745-9125}, url={http://dx.doi.org/10.1111/1745-9125.70048}, DOI={10.1111/1745-9125.70048}, journal={Criminology}, publisher={Wiley}, author={Barnum, Timothy C. and Herman, Shaina and Nagin, Daniel S. and Pickett, Justin T.}, year={2026}, month=Apr }
| 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 |