There’s a recurrent interest in statistics that can be used to predict team success and when they appear to show that how much a club spends in the best predictor, that appears to confirm conventional wisdom.
John Burn-Murdoch and Gavin Jackson have been writing a weekly series of articles in the Financial Times looking at sports statistics and what they tell us. In their latest article they set out to replicate an analysis undertaken by Stefan Szymanski and Simon Kuper in their well-known book Soccernomics, but using contemporary data.
There’s a recurrent interest in statistics that can be used to predict team success and when they appear to show that how much a club spends in the best predictor, that appears to confirm conventional wisdom.
John Burn-Murdoch and Gavin Jackson have been writing a weekly series of articles in the Financial Times looking at sports statistics and what they tell us. In their latest article they set out to replicate an analysis undertaken by Stefan Szymanski and Simon Kuper in their well-known book Soccernomics, but using contemporary data.
Using the final Premier League standings from 2000/2001 through to last season and Deloitte’s financial data, they plotted the average finishing position for every team that has played in the Premiership against the average of its wage bills relative to the league average for a given season.
The result was a R-squared (a standard statitsical measure varying between -1.0 and +1.0) of 0.67. As a result, they claim that wages explain 67 per cent of variation in final league standings, compared to just 47 per cent at the time they wrote. They conclude that 80 per cent of the variation in final standings in the Premier League ‘can be explained even before the season gets under way simply by looking at a club’s wage bill.’
Unfortunately, it may not be that simple. A letter in the Pink ‘Un today points out, ‘They assume that a statistical relationship based on averages will hold out just as strongly for a single season. This is not the case as their averages smooth out the noise in the data.’
The letter writer, Don Altman, reckons that wage bills have explained only about 50 to 60 per cent of the variation in final positions for several seasons. That is still quite a lot, but leaves plenty of room for what is probably the next most important variable, managerial skill. Injuries and suspensions may also have some effect.
So if we take the case of Newcastle United, a large part of their current position may be explained by the short termism and cost cutting of owner Mike Ashley. However, much criticised manager Alan Pardew must take his share of the blame.