2,395 rated or chosen profiles from 2,395 respondents, in up to 1 tasks of 1 profile varying on 4 attributes.

About this table

Description	Factorial vignette (2 x 3 x 3 x 3) in which 2,395 Danish panel respondents (Voxmeter, before the November 2017 municipal election) each read one description of a fictitious municipal candidate varying gender (first name), parents' occupation, own occupation and an elderly-care policy statement. Outcomes: likelihood of voting for the candidate (rating), left-right placement and eight trait ratings.
Reference	Pedersen, R. T., Dahlgaard, J. O., & Citi, M. (2019). Voter reactions to candidate background characteristics depend on candidate policy positions. Electoral Studies, 61, 102066.
DOI	10.1016/j.electstud.2019.102066
Licence	CC0 1.0
Source data	https://doi.org/10.7910/DVN/B5SWDJ

Notes

Conjoint table (irw_conjoint_2). One text vignette per respondent; rating = likelihood of voting for the candidate 0 (very unlikely) - 10 (very likely); rating_left_right = candidate placement 0-10 (0 = left); rating_<trait> = how well eight words describe the candidate, 1-5, anchors not in the deposit (higher = describes better, inferred from the paper's results). Don't-know codes are NA as in the authors' code; parents/job/policy clauses left out of the text are '(not shown)'. 2,395 respondents with an outcome (2,400 completed per the paper; 34 completers answered don't know throughout, 29 partial completers kept); vote means by policy arm reproduce the paper.

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

Design

Topic	candidate choice
A profile represents	person
Country	DK
Language shown	da
Language of stored levels	da
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	Likelihood of voting for the candidate, assuming the candidate ran in the respondent's own municipality (paraphrase) [rating, 0 (very unlikely) to 10 (very likely)]
rating_caring	How well or poorly does the word 'caring' describe the candidate? (paraphrase; Danish trait items from Pedersen 2017) [rating, 1 (unknown) to 5 (unknown)]
rating_competent	How well or poorly does the word 'competent' describe the candidate? (paraphrase; Danish trait items from Pedersen 2017) [rating, 1 (unknown) to 5 (unknown)]
rating_conscientious	How well or poorly does the word 'conscientious' describe the candidate? (paraphrase; Danish trait items from Pedersen 2017) [rating, 1 (unknown) to 5 (unknown)]
rating_credible	How well or poorly does the word 'credible' describe the candidate? (paraphrase; Danish trait items from Pedersen 2017) [rating, 1 (unknown) to 5 (unknown)]
rating_friendly	How well or poorly does the word 'friendly' describe the candidate? (paraphrase; Danish trait items from Pedersen 2017) [rating, 1 (unknown) to 5 (unknown)]
rating_intelligent	How well or poorly does the word 'intelligent' describe the candidate? (paraphrase; Danish trait items from Pedersen 2017) [rating, 1 (unknown) to 5 (unknown)]
rating_knowledgeable	How well or poorly does the word 'knowledgeable' describe the candidate? (paraphrase; Danish trait items from Pedersen 2017) [rating, 1 (unknown) to 5 (unknown)]
rating_left_right	Placement of the candidate's economic-policy position on an 11-point left-right scale (paraphrase) [rating, 0 (left) to 10 (right)]
rating_likeable	How well or poorly does the word 'likeable' describe the candidate? (paraphrase; Danish trait items from Pedersen 2017) [rating, 1 (unknown) to 5 (unknown)]

Columns

attr_jobattr_nameattr_parentsattr_policycov_agecov_completedcov_educationcov_gendercov_left_rightcov_regioncov_vote_choiceidprofileratingrating_caringrating_competentrating_conscientiousrating_crediblerating_friendlyrating_intelligentrating_knowledgeablerating_left_rightrating_likeabletask

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("pedersen_2019_candidate_background", source = "conj")

# Python
pip install irw

import irw
df = irw.fetch("pedersen_2019_candidate_background", source="conj")

How to cite

@article{Pedersen_2019, title={Voter reactions to candidate background characteristics depend on candidate policy positions}, volume={61}, ISSN={0261-3794}, url={http://dx.doi.org/10.1016/j.electstud.2019.102066}, DOI={10.1016/j.electstud.2019.102066}, journal={Electoral Studies}, publisher={Elsevier BV}, author={Pedersen, Rasmus T. and Dahlgaard, Jens Olav and Citi, Manuele}, year={2019}, month=Oct, pages={102066} }

Respondents	2,395
Rows (one per respondent, task and profile)	2,395
Tasks per respondent (most)	1
Profiles per task	1
Attributes	4

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

pedersen_2019_candidate_background