Consistency among alternative performance measures in an applied judgement setting |
| |
| Affiliation: | 1. Research Centre of the Centre Hospitalier Universitaire (CHU) Sainte-Justine, Montreal, Quebec, Canada;2. International Centre for Comparative Criminology, University of Montreal, Montreal, Quebec, Canada;3. Department of Criminology, University of Ottawa, Ottawa, Ontario, Canada;4. PERFORM Centre, Department of Exercise Science, Concordia University, Montreal, Quebec, Canada;5. Département des sciences humaines, Université Sainte-Anne, Pointe-de-L''Église, Nouvelle-Écosse, Canada;1. Judith Lumley Centre, La Trobe University, Bundoora, VIC 3086, Australia;2. School of Nursing & Midwifery, La Trobe University, Bundoora, VIC 3086, Australia;3. The Royal Women’s Hospital, Locked Bag 300, Cnr Grattan St and Flemington Rd, Parkville, VIC 3052, Australia;1. School of Nursing, Faculty of Health Sciences, Queen''s University, Canada;2. School of Nursing and Department of Public Health Sciences, Faculty of Health Sciences, Queen''s University, Canada;3. School of Health Policy & Management, York University, Canada;4. School of Nursing and Department of Anesthesiology & Perioperative Medicine, Faculty of Health Sciences, Queen''s University, 92 Barrie Street, Kingston, Ontario K7L 3N6, Canada;1. Graduate School of Humanities and Social Sciences, Hiroshima University, 1-5-1 Kagamiyama, Higashi-Hiroshima, Hiroshima, 739-8529, Japan;2. The IDEC Institute, Network for Education and Research on Peace and Sustainability (NERPS), Hiroshima University, 1–5–1 Kagamiyama, Higashi-Hiroshima, Hiroshima, 739–8529, Japan;3. Hitotsubashi Institute for Advanced Study, Hitotsubashi University, 2-1 Naka, Kunitachi, Tokyo, 186-8601, Japan |
| |
| Abstract: | The extent to which different performance measures can lead to different conclusions about human performance is investigated in a task involving the prediction of experts' ratings of the quality of corporate bonds. Results produced by the traditional correlational performance measure - with respect to both the relative performance of ‘man’ versus model and the effects of feedback on performance - are compared with results produced by five alternative measures including mean absolute error, mean squared error, and various types of ‘hit rates’. The correlational measure produces results that are moderately consistent with those produced by the other five measures in this applied prediction setting. Potential implications of using alternative performance measures in applied settings, especially the need to identify appropriate loss functions, are emphasized. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
