analysis of variance
A statistical method that partitions the total variation in an outcome among separate sources, such as leader, industry, company, and year, to estimate how much each contributes.
As defined in 367 | Jared Diamond on the Course of History and the Role of leaders
Where it comes up · 1
Most important claims · 4 of 4Search all claims for “analysis of variance” →
- Coaches are often fired after a losing season, but much of that losing reflects random factors, so by regression to the mean the next season tends to improve regardless; the right test compares next-year performance with and without firing, which shows the coach's real effect is smaller than naive comparisons suggest.367 | Jared Diamond on the Course of History and the Role of leaders
- Coaches have a larger effect on outcomes in college sports than in professional sports, because professional rosters turn over less predictably and star players, such as Tom Brady, dominate results across coaching changes.367 | Jared Diamond on the Course of History and the Role of leaders
- Business school and public policy researchers developed statistical methods for measuring coach effects in sports and then applied them to CEOs and politicians, finding that governors hold more power than city mayors, with Los Angeles mayoral turnout only about 20 percent.367 | Jared Diamond on the Course of History and the Role of leaders
- Allison Mackie's study of CEOs who switched companies attributed about 30 percent of profit variation to the leader, about 20 percent each to the industry and the company, and about 3 percent to the year, and when non-switching CEOs were included the CEO share fell to roughly 15 percent.367 | Jared Diamond on the Course of History and the Role of leaders