12,351 rated or chosen profiles from 224 respondents, in up to 20 tasks of 3 profiles varying on 6 attributes.
| Description | Researchers in an online survey (2018-19, n = 224, mostly economists and social scientists) ranked 20 fixed sets of 3 fictitious publications described only by six metrics (citations, tweets, Mendeley readers, downloads, journal impact factor, h-index); outcomes are the first pick and the full rank. |
|---|---|
| Reference | Lemke, S., Mazarakis, A., & Peters, I. (2021). Conjoint analysis of researchers' hidden preferences for bibliometrics, altmetrics, and usage metrics. Journal of the Association for Information Science and Technology, 72(6), 777-792. |
| DOI | 10.1002/asi.24445 |
| Licence | CC BY 4.0 |
| Source data | https://doi.org/10.5281/zenodo.3560886 |
These notes describe the source data, which the IRW reproduces as released. All notes are listed on the Data Notes page.
| Respondents | 224 |
|---|---|
| Rows (one per respondent, task and profile) | 12,351 |
| Tasks per respondent (most) | 20 |
| Profiles per task | 3 |
| Attributes | 6 |
| Tasks with no profile chosen | 0 |
| Topic | other |
|---|---|
| A profile represents | message |
| Country | unknown |
| Language shown | en |
| Language of stored levels | en |
| Randomization restrictions | yes (stated by the source): fixed design: the same 20 choice sets of 3 out of 20 fictitious publications for every respondent, chained (each set shares one publication with the next); only the 20 publications' metric combinations occur, and level shares are unequal (e.g. citations 0/5/250 in 31/31/20% of rows) |
| Task order | recorded in the deposit |
| Profile position | unknown |
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.
Outcomes:
| choice | Rank the publications: publication picked first among the three (paraphrase) [choice, forced] |
|---|---|
| rating_rank | Rank the publications (paraphrase); 1 = picked first, 2 = picked second, 3 = remaining [rating, 1 (ranked first (most preferred)) to 3 (ranked last)] |
attr_citationsattr_downloadsattr_h_indexattr_journal_impact_factorattr_mendeley_readersattr_tweetschoicecov_birth_yearcov_countrycov_disciplinecov_fav_indicatorcov_gendercov_rolecov_workplacecov_years_experienceidprofilerating_ranktask
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("lemke_2021_research_metrics", source = "conj")
# Python
pip install irw
import irw
df = irw.fetch("lemke_2021_research_metrics", source="conj")
@article{Lemke_2021, title={Conjoint analysis of researchers’ hidden preferences for bibliometrics, altmetrics, and usage metrics}, volume={72}, ISSN={2330-1643}, url={http://dx.doi.org/10.1002/asi.24445}, DOI={10.1002/asi.24445}, number={6}, journal={Journal of the Association for Information Science and Technology}, publisher={Wiley}, author={Lemke, Steffen and Mazarakis, Athanasios and Peters, Isabella}, year={2021}, month=Jan, pages={777–792} }
| 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 |