A comparison of statistical models in predicting violence in psychotic illness

TY - JOUR

T1 - A comparison of statistical models in predicting violence in psychotic illness

AU - Thomas, S

AU - Leese, M

AU - Walsh, E

AU - McCrone, P

AU - Moran, P

AU - Burns, T

AU - Creed, F

AU - Tyrer, P

AU - Fahy, T

PY - 2005/7

Y1 - 2005/7

N2 - Background: The application of statistical modeling techniques, including classification and regression trees, in the prediction of violence has increasingly received attention. Methods: The predictive performance of logistic regression and classification tree methods in predicting violence was explored in a sample of patients with psychotic illness. Results: Of 2 logistic regression models, the forward stepwise method produced a simpler model than the full model, but the latter performed better. The performance of the classification tree appeared to be high before cross-validation, but reduced when cross-validated. The standard logistic model was the most robust model. A simplified tree with extra weight given to violent cases was a reasonable competitor and was simple to apply. Conclusion: Although classification trees can be suitable for routine clinical practice, because of the simplicity of their decision-making processes, their robustness and therefore clinical utility was problematic in this sample. Further research is required to compare such models in large prospective epidemiologic studies of other psychiatric populations. (c) 2005 Elsevier Inc. All rights reserved

AB - Background: The application of statistical modeling techniques, including classification and regression trees, in the prediction of violence has increasingly received attention. Methods: The predictive performance of logistic regression and classification tree methods in predicting violence was explored in a sample of patients with psychotic illness. Results: Of 2 logistic regression models, the forward stepwise method produced a simpler model than the full model, but the latter performed better. The performance of the classification tree appeared to be high before cross-validation, but reduced when cross-validated. The standard logistic model was the most robust model. A simplified tree with extra weight given to violent cases was a reasonable competitor and was simple to apply. Conclusion: Although classification trees can be suitable for routine clinical practice, because of the simplicity of their decision-making processes, their robustness and therefore clinical utility was problematic in this sample. Further research is required to compare such models in large prospective epidemiologic studies of other psychiatric populations. (c) 2005 Elsevier Inc. All rights reserved

U2 - 10.1016/j.comppsych.2004.10.001

DO - 10.1016/j.comppsych.2004.10.001

M3 - Article

VL - 46

SP - 296

EP - 303

JO - Comprehensive Psychiatry

JF - Comprehensive Psychiatry

IS - 4

ER -