About the study

Bayesian Conditional Process Model of Home Advantage or Home advantage mediated (HAM) model

The interplay between Venue, Team Performance, Referees’ Decisions, and Outcome (the circular shape denotes latent variables—with the individual variables listed within the boxes). Lines with single-end arrows indicate the direction of influence. The numbers on the line are path model coefficients. The pre-Covid path coefficients are in blue, the post-Covid coefficients are in red, while their differences, indicated also by Δ, are in black. The statistically significant coefficients (95% credible intervals do not encompass 0) are indicated with . The difference between the pre- and post-Covid path coefficients, delta (∆), is indicated above the individual coefficients ( when 95% credible intervals do not encompass 0 and ns when they do). The indirect influence of Venue on Outcome through Team Performance and Referees’ Decisions is formally tested in a mediation model (upper left box). The indirect influence of Venue on Referees’ Decision through Team Performance is also formally tested by mediation (lower left box). R2 is Bayesian full model coefficient of determination, which includes both fixed (COVID, Venue, Referees’ Decisions, Team Performance, Importance, and Rating) and random (league and team) effects. The control variables, Rating and Importance, were not presented here for the sake of conciseness.

Using this approach, we show that team performance (how much more aggressive the home team is) reduces significantly without the audience. They end up being only half as dominant as with spectators. The referees’ decisions also change towards home teams. When the audience is present they get fewer warnings than away teams, but once the audience is absent they are warned more often than the away teams. Team performance also switches the sign when it comes to influencing referees’ behaviour when with and without an audience. According to our model, the Home advantage reduction is primarily driven by the crowd’s indirect influence on the result through the home team’s performance and referees’ decision (allowing more dominating or aggressive behaviour).

You can find complete data and code + additional models and analyses on the Open Science Framework (OSF) page

About the nightmarish editorial process

I think that this was the most atrocious editorial process that I ever witnessed. This is an excerpt from my co-author on the process: “Extremely long and frustrating processing time. The article went through several rounds of revision and would get kicked back by quality check for different things that weren’t identified in previous rounds, each time taking a week to go through another quality check…” You can find the complete version here

Insult to injury

The thing that irked me the most is their insistence to change the title of our study. It was not descriptive enough! I mean, that is a decent request; the first version of the title was perhaps problematic. So we go and change that and propose “The (Missing) 12th Man: Home Advantage Mediated (HAM) by Referee Bias and Team Performance During Covid”. We should have everything there: factors that we focus on, audience effect (covid versus pre-covid) and statistical modelling (mediation). Plus we have our personal touch in the first part of the title. This version is on PsyArXiv.

However, the technical editor complains again and wants us to take out the “The (Missing) 12th Man” as they do not find it descriptive enough, that (missing) part is ambiguous, and that 12th man would perhaps be understood by football fans, but they will not be primary readers of this paper (why?! - I am planning to forward the paper to the Manager of Sheffield United - Slaviša Jokanović, if by any chance he forwards it to some of his supporting staff I will get more readers than on most of my papers). We end up in trenches, we refuse to change the title and argue against it. They insist on us changing it. Each correspondence takes a full week - we respond in a day and then they respond 7 days later. My view was to withdraw the paper. However, we already spent over 8 months conversing using this weird version of digital snail mail. Finally, we change the title, cough up something above 1,600 pounds for the publication fees and now they ask us to share the paper on social networks!