Premium
Modelling employment durations of NHL head coaches: turnover and post‐succession performance
Author(s) -
Audas Rick,
Goddard John,
Rowe W. Glenn
Publication year - 2006
Publication title -
managerial and decision economics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.288
H-Index - 51
eISSN - 1099-1468
pISSN - 0143-6570
DOI - 10.1002/mde.1259
Subject(s) - league , mean reversion , hazard , demographic economics , dependency (uml) , operations management , psychology , actuarial science , economics , econometrics , computer science , chemistry , physics , software engineering , organic chemistry , astronomy
Match‐level National Hockey League (NHL) data are used to identify factors likely to trigger the departure of a team's coach, and to measure the short‐term impact on subsequent match results. There is a statistically significant link between individual match results and the job departure hazard for up to 15 games prior to the point of departure. The hazard depends on the team's current standing within its conference relative to a pre‐season forecast, recent performance in the Stanley Cup, the coach's age and previous employment with his present team as a player. After controlling for a mean‐reversion effect, teams that changed their coach within‐season are found to perform worse subsequently than those that did not, but the negative effect is short‐lived. Copyright © 2006 John Wiley & Sons, Ltd.