Effect of racial misclassification in police data on estimates of racial disparities
Bibliographic record
Abstract
Abstract Research on race and policing increasingly draws upon data collected by police officers to estimate racial disparities in police contact. Many of these data sets, however, rely on officer perception of a stopped person's race, which may be inconsistent with how those individuals self‐identify. Furthermore, researchers frequently benchmark contact data where race is perceived by police officers against census and survey data where race is self‐identified. We argue that discordance between how individuals self‐identify and how they are classified by officers can bias estimates of racial disparities. Using a unique data set, which allows us to compare officers’ racial classification of stopped persons with those same persons’ racial self‐identification, we characterize rates of racial misclassification in administrative police records. We find evidence of racial misclassification in police records, especially among Hispanic and Asians/Pacific Islanders. We find that officer classification of Hispanics as (non‐Hispanic) White is the most common form of racial misclassification in our sample and that its substantive consequences are significant. Specifically, we find that officer classification of Hispanics as White may lead analysts to incorrectly conclude that Hispanics are no more likely than Whites to be cited by police.
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 | 0.108 | 0.407 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.004 | 0.005 |
| Science and technology studies | 0.002 | 0.003 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".