12,384 rated or chosen profiles from 3,096 respondents, in up to 2 tasks of 2 profiles varying on 8 attributes.

About this table

Description	Candidate conjoint: 3,096 Italian adults in wave 2 (May-June 2019) of the Siena/GfK Italy probability panel each compared 2 pairs of hypothetical European Parliament candidates varying 8 traits (gender, job, communication style, social skills, integrity, competence, view of role, leadership) and chose which they would prefer to win a seat.
Reference	Martini, S., & Olmastroni, F. (2021). From the lab to the poll: The use of survey experiments in political research. Italian Political Science Review / Rivista Italiana di Scienza Politica, 51(2), 231-249.
DOI	10.1017/ipo.2021.20
Licence	CC0 1.0
Source data	https://doi.org/10.7910/DVN/AG0JK6

Notes

Conjoint table (irw_conjoint). choice = which of the two candidates the respondent would have preferred to win a seat in the European Parliament (forced choice, no opt-out; article's English). Levels are the authors' English labels (respondents saw Italian); all 3,096 respondents are kept, including 420 who saw the rare 'artisan' job level that the article's main analysis (n = 2,676) excludes; the 7-point rating is not built because only a dichotomized version was deposited. Attribute order was randomized but not recorded; cov_attention_pass flags the authors' attention subsample.

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	IT
Language shown	it
Language of stored levels	en
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:

choice	Which of the two candidates would you personally have preferred to win a seat in the European Parliament? (paraphrase) [choice, forced]

Columns

attr_communicationattr_competenceattr_genderattr_integrityattr_jobattr_leadershipattr_social_skillsattr_vision_of_rolechoicecov_attention_passcov_pop1_w1cov_pop1_w2cov_pop2_w1cov_pop2_w2cov_pop3_w1cov_pop3_w2cov_pop4_w1cov_pop4_w2cov_pop5_w1cov_pop5_w2cov_pop6_w1cov_pop6_w2cov_survey_weightidprofiletask

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("martini_2021_good_politician", source = "conj")

# Python
pip install irw

import irw
df = irw.fetch("martini_2021_good_politician", source="conj")

How to cite

@article{Martini_2021, title={From the lab to the poll: The use of survey experiments in political research}, volume={51}, ISSN={2057-4908}, url={http://dx.doi.org/10.1017/ipo.2021.20}, DOI={10.1017/ipo.2021.20}, number={2}, journal={Italian Political Science Review/Rivista Italiana di Scienza Politica}, publisher={Cambridge University Press (CUP)}, author={Martini, Sergio and Olmastroni, Francesco}, year={2021}, month=May, pages={231–249} }

Respondents	3,096
Rows (one per respondent, task and profile)	12,384
Tasks per respondent (most)	2
Profiles per task	2
Attributes	8
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

martini_2021_good_politician