6,526 rated or chosen profiles from 1,089 respondents, in up to 3 tasks of 2 profiles varying on 5 attributes.

About this table

Description	Paired pictograph conjoint in eastern Liberia: 1,089 adults in refugee-host communities chose which of two hypothetical Ivorian refugee families to host in 3 rounds, with household-head gender, ethnicity (co-ethnic or not), religion, occupation and food security randomized; outcome is the forced choice.
Reference	Hartman, A. C., & Morse, B. S. (2020). Violence, empathy and altruism: Evidence from the Ivorian refugee crisis in Liberia. British Journal of Political Science, 50(2).
DOI	10.1017/S0007123417000655
Licence	CC0 1.0
Source data	https://doi.org/10.7910/DVN/X1TGCJ

Notes

Conjoint table (irw_conjoint). Three paired tasks shown as pictographs; choice = which of two refugee families the respondent would host (paraphrase; forced choice, no opt-out). Levels are the authors' Table 1 labels; ethnicity is relative (co-ethnic / not co-ethnic); co-ethnic non-co-religious profiles were excluded for respondents from religiously homogeneous groups. task/profile inferred from row order; 2 respondents and 4 tasks with missing attributes dropped; N = 1,089 (manuscript 1,230).

These notes describe the source data, which the IRW reproduces as released. All notes are listed on the Data Notes page.

Design

Topic	immigration asylum
A profile represents	person
Country	LR
Language shown	unknown
Language of stored levels	en
Randomization restrictions	yes (stated by the source): co-ethnic but not co-religious profiles excluded for respondents from ethnic groups predominantly of one religion (~30% of sample; e.g. no co-ethnic Muslim family for Grebo respondents)
Task order	inferred from row order
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	Imagine a new crisis in which more refugees seek refuge than your community can host: which of these two refugee families would you host? (paraphrase) [choice, forced]

Columns

attr_ethnicityattr_foodattr_gender_hhattr_occupationattr_religionchoicecov_gendercov_muslimcov_warvictidprofiletasktrial_prime

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.

Get the data

Download CSVno account needed Browse on Redivisexplore and query Croissant metadataHugging Face, Kaggle, OpenML

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("hartman_2020_refugee_hosting", source = "conj")

# Python
pip install irw

import irw
df = irw.fetch("hartman_2020_refugee_hosting", source="conj")

How to cite

@article{Hartman_2018, title={Violence, Empathy and Altruism: Evidence from the Ivorian Refugee Crisis in Liberia}, volume={50}, ISSN={1469-2112}, url={http://dx.doi.org/10.1017/S0007123417000655}, DOI={10.1017/s0007123417000655}, number={2}, journal={British Journal of Political Science}, publisher={Cambridge University Press (CUP)}, author={Hartman, Alexandra C. and Morse, Benjamin S.}, year={2018}, month=Jan, pages={731–755} }

Respondents	1,089
Rows (one per respondent, task and profile)	6,526
Tasks per respondent (most)	3
Profiles per task	2
Attributes	5
Tasks with no profile chosen	0

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

hartman_2020_refugee_hosting