Disclosing sample bias fails to fully correct judgments of partisan extremity
Bibliographic record
Abstract
How do we infer the beliefs of an entire group (e.g., Democrats) after being exposed to the beliefs of only a handful of group members? What if we know that the beliefs we encountered were selected in a biased manner? Across two experiments, we recruited 640 U.S. residents and assessed whether they could recognize and correct for such sample bias. Some participants viewed biased samples that exclusively featured the political opinions of extreme partisans, while others viewed representative samples free from selection biases. Results suggest that people do attempt to correct for known sample bias, but their efforts are often insufficient, leading them to make inaccurate inferences that align with sample bias. Specifically, participants tended to overestimate the ideological extremity of both Democrats and Republicans to a greater extent when exposed to explicitly biased samples, as opposed to representative ones. They also perceived members of the political party in question as holding more homogenous views, presumably because samples of extreme party members' views tend to have less variability than representative samples. Perhaps as a consequence, participants exposed to what they knew to be a biased sample, and who subsequently gave more biased estimates, did not express lower confidence in their estimates compared to participants who were shown representative samples. We discuss how a tendency to insufficiently adjust for transparently biased samples may contribute to partisan misperceptions that fuel political polarization.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.020 | 0.127 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".