Win-stay lose-shift strategy in formation changes in football

EPJ Data Science

Table 9 Results of the GLMM analysis for the Fussballdaten data when all the independent variables were considered

Variable	Coefficient	SE	p -value
\(\mathrm{Win}_{t-1}\)	−0.568	0.038	<0.001
\(\mathrm{Win}_{t-2}\)	−0.234	0.038	<0.001
\(\mathrm{Loss}_{t-1}\)	0.404	0.038	<0.001
\(\mathrm{Loss}_{t-2}\)	0.018	0.037	0.628
\(\mathrm{Win}_{t-1} \times\mathrm{ Win}_{t-2}\)	0.118	0.056	0.035
\(\mathrm{Loss}_{t-1} \times\mathrm{ Loss}_{t-2}\)	0.071	0.058	0.220
Home	−0.174	0.026	<0.001
Strength	0.026	0.078	0.740

\(\mathrm{Win}_{t-i}\) (i = 1,2) is the binary variable representing whether or not the team has won the (t − i)th match (0: no win, 1: win). Likewise for \(\mathrm{ Loss}_{t-i}\) (i = 1,2) (0: no loss, 1: loss). Home is equal to 0 for an away game and 1 for a home game. Strength is equal to the fraction of the matches that the team has won in a season. SE: standard error.