40,976 rated or chosen profiles from 1,815 respondents, in up to 13 tasks of 2 profiles varying on 2 attributes.

One of 2 tables from the same source; this one is the news_selection table. The others are listed under Related tables.

About this table

Description	US MTurk workers (2021; 1,815 respondents) chose which of two news articles (headline and source: Fox News, MSNBC, USA Today) they would prefer to read over 12 pairs, randomly assigned to a forced-choice arm or an arm allowing 'Neither', then answered one repeated pair in the other format; a replication of Mummolo (2016).
Reference	Miller, D. R., & Ziegler, J. (2024). Preferential abstention in conjoint experiments. Research & Politics, 11(4).
DOI	10.1177/20531680241299329
Licence	CC0 1.0
Source data	https://doi.org/10.7910/DVN/JQOPNW

Notes

Conjoint table (irw_conjoint). choice: "Would you prefer to read News Selection A or News Selection B?"; OPT-OUT in the abstention format only ("Neither": choice = 0 on both profiles, about 25% of abstention-format tasks); forced format has no opt-out. trial_arm / trial_format / trial_repeat_of identify the arm and the repeated 13th task. Two attributes (headline, source), row order randomized and recorded; restrictions undocumented. All respondents with an answered task kept (no screening applied, as in the authors' code).

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

Design

Topic	political communication
A profile represents	message
Country	US
Language shown	en
Language of stored levels	en
Randomization restrictions	unknown
Task order	recorded in the deposit
Profile position	recorded in the deposit

Outcomes:

choice	Would you prefer to read News Selection A or News Selection B? [choice, opt-out allowed]

Columns

attr_headlineattr_sourceattrpos_headlineattrpos_sourcechoicecov_birth_yearcov_cigarettescov_dem_strengthcov_educationcov_gendercov_health_insurancecov_health_jobcov_hispaniccov_ideologycov_incomecov_ind_leancov_losing_weightcov_party_idcov_racecov_rep_strengthcov_studentidprofiletasktrial_armtrial_formattrial_repeat_of

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("miller_2024_news_selection", source = "conj")

# Python
pip install irw

import irw
df = irw.fetch("miller_2024_news_selection", source="conj")

How to cite

@article{Miller_2024, title={Preferential abstention in conjoint experiments}, volume={11}, ISSN={2053-1680}, url={http://dx.doi.org/10.1177/20531680241299329}, DOI={10.1177/20531680241299329}, number={4}, journal={Research &amp; Politics}, publisher={SAGE Publications}, author={Miller, David R. and Ziegler, Jeffrey}, year={2024}, month=Oct }

Respondents	1,815
Rows (one per respondent, task and profile)	40,976
Tasks per respondent (most)	13
Profiles per task	2
Attributes	2
Tasks with no profile chosen	2,577

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

miller_2024_news_selection