Goldman Sachs: it isn’t coming home

{"text":[[{"start":5.95,"text":"Happy Friday. Goldman Sachs thinks conventional rankings are not sufficiently bearish on England’s chances at the World Cup this summer:"}],[{"start":null,"text":"

We present a model for predicting the outcome of the 2026 World Cup in the US, Canada and Mexico from June 11 to July 19. It is similar to our model for prior World Cups but extended along several dimensions.

[…]

The model says that Spain has a 26% probability of winning the trophy, followed by France at 19%, Argentina at 14%, Brazil at 8% and England at 5%. Spain is predicted to win because it has the highest Elo ranking, supported by scoring talent and good momentum into the competition. Argentina is penalised by the “winner’s slump”, i.e. the statistical underperformance of reigning champions in the following World Cup; France suffers from likely facing top-ranked Spain in the semifinals; and England underperforms its Elo rating given historical tournament disappointment, geographical headwinds (likely facing Mexico in high-altitude Mexico City), and a slightly unlucky draw.

"}],[{"start":14.75,"text":"Most of the bank’s analysis in derived from the various national teams’ Elo rankings, together with a regression model that uses a team’s scores against different opponents over “the entire history of mandatory international matches since 1978”. Jan Hatzius and team work on the reasonable assumption that scoring more goals is rarer than scoring fewer:"}],[{"start":null,"text":""}],[{"start":36.15,"text":"What this might tell us about the first ever England vs Curaçao clash, should it happen, is unclear."}],[{"start":42.449999999999996,"text":"A simple comparison of Elo ratings and FIFA rankings (a similar system) put La Roja in pole position, with France and defending champions Argentina a little behind."}],[{"start":null,"text":""}],[{"start":52.5,"text":"They build on this analysis by integrating extra variables: scoring talent, momentum, mentality and geography. On mentality they write, in words that will ring true to about 58.6mn people:"}],[{"start":null,"text":"

[We] find that reigning world champions typically underperform (while teams at their first World Cup usually outperform) and that it is more difficult to score against European teams (all else equal). Furthermore, major footballing nations generally get a World Cup boost, with the notable exception of England.

"}],[{"start":65.2,"text":"We have some reservations about this methodology, including the implied relevance of whatever the country’s five most recent competitive games (which will vary greatly in terms of opposition and importance) and a “scoring talent” model that appears to account for nationality but not selection (poor Dominic Calvert-Lewin). As they acknowledge:"}],[{"start":null,"text":"

While our expanded model accounts for a larger set of factors than our previous attempts, it remains largely blind to the non-attacking talent (e.g. the depth of the French and Portuguese midfield and wings or the role of good keepers in a penalty shootout), health (will Lamine Yamal’s recent injury weigh on his performance in the World Cup?), individual momentum (will the many French players at PSG benefit from their deep run in the Champions League? Will Messi and Ronaldo be competitive after a few years away from top European football?), or managerial experience (an Ancelotti effect for Brazil?).

"}],[{"start":83.30000000000001,"text":"Anyway, here’s another encouraging chart:"}],[{"start":null,"text":""}],[{"start":87.50000000000001,"text":"Utilising this model, Goldman ran 50,000 simulated cup runs, which exclude the possibility of knockout draws for reasons that presumably favour England:"}],[{"start":null,"text":"

In the knock-out stage, we avoid draws by “burning” Monte Carlo draws that involve the same number of goals by the two teams. This mechanically boosts the chances of the team with the slightly higher mean predicted number of goals.

"}],[{"start":97.90000000000002,"text":"Cronch cronch goes the data, and (according to the model) the most likely outcome is that the Three Lions get knocked out by Brazil in the round of 16 (zoomable)"}],[{"start":null,"text":""}],[{"start":107.40000000000002,"text":"The conclusion is more bullish than the bookies for Spain, and quite a bit more pessimistic for England:"}],[{"start":null,"text":""}],[{"start":113.30000000000003,"text":"So if you’re planning to put any money / emotional investment into England this World Cup, ask yourself this: who do you trust more, gambling companies or investment banks?"}],[{"start":123.95000000000003,"text":"Still, could be worse:"}],[{"start":null,"text":""}],[{"start":125.95000000000003,"text":"Further reading:"}],[{"start":127.35000000000004,"text":"— World Cup madness"}],[{"start":135.15000000000003,"text":""}]],"url":"https://audio.ftcn.net.cn/album/a_1780105919_4415.mp3"}