Construct Measurement Quality Improves Predictive Accuracy in Violence Risk Assessment: an Illustration Using the Personality Assessment Inventory
Bibliographic record
Abstract
Much of the risk assessment literature has focused on the predictive validity of risk assessment tools. However, these tools often comprise a list of risk factors that are themselves complex constructs, and focusing on the quality of measurement of individual risk factors may improve the predictive validity of the tools. The present study illustrates this concern using the Antisocial Features and Aggression scales of the Personality Assessment Inventory (Morey, 1991). In a sample of 1,545 prison inmates and offenders undergoing treatment for substance abuse (85% male), we evaluated (a) the factorial validity of the ANT and AGG scales, (b) the utility of original ANT and AGG scales and newly derived ANT and AGG scales for predicting antisocial outcomes (recidivism and institutional infractions), and (c) whether items with a stronger relationship to the underlying constructs (higher factor loadings) were in turn more strongly related to antisocial outcomes. Confirmatory factor analyses (CFAs) indicated that ANT and AGG items were not structured optimally in these data in terms of correspondence to the subscale structure identified in the PAI manual. Exploratory factor analyses were conducted on a random split-half of the sample to derive optimized alternative factor structures, and cross-validated in the second split-half using CFA. Four-factor models emerged for both the ANT and AGG scales, and, as predicted, the size of item factor loadings was associated with the strength with which items were associated with institutional infractions and community recidivism. This suggests that the quality by which a construct is measured is associated with its predictive strength. Implications for risk assessment are discussed.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".