A Fresh Shot at Statistics in the Classroom: Three Perspectives Using World Cup Soccer Player Data

Figures & data

Table 1 Summary table for the FIFA World Cup soccer player dataset.

	Min	Q1	Med	Q3	Max	Mean	Std Dev
Age (yrs)	16	24	27	30	45	26.8	4.08
Men	19	25	27	30	45	27.4	3.96
Women	16	23	26	29	41	26	4.09
Caps	0	11	26	59	282	39.4	38.2
Men	0	10	25	52	158	35.4	32.0
Women	0	12	29	66.2	282	45.2	45.2
Goals	0	0	1	6	181	5.77	12.3
Men	0	0	1	5	81	4.52	8.81
Women	0	0	1	8	181	7.56	15.8
	GK	DF	FW	MF
Position	168 (0.130)	423 (0.328)	296 (0.230)	401 (0.311)
Men	96 (0.130)	247 (0.336)	158 (0.215)	235 (0.319)
Women	72 (0.130)	176 (0.319)	138 (0.250)	166 (0.301)

Five number summaries, mean, and standard deviation are reported for numerical variables; counts (and relative frequencies) for the categorical variable. Note that for position: GK $=$ Goalkeeper, DF $=$ Defender, FW $=$ Forward, and MF $=$ Midfielder.

Fig. 1 Example table to use in class to keep track of teams with shared birthdays.

Fig. 2 Histogram of empirical probabilities for large n.

Fig. 3 Illustration of the law of large numbers.

Fig. 4 Example snippet from the original 2018 FIFA World Cup data frame (called playersM in the given R code).

Fig. 5 Proportion of players born in each month of the year, computed separately by men and women.

Fig. 6 Proportion of players born on each day of the month, computed separately by men and women.

Fig. 7 Scatterplot and LOESS curve for the relationship between age (in years) and goals scored.

Fig. 8 Scatterplot and LOESS curves for the relationship between age (in years) and goals scored separated by position and compared across the 2018 FIFA World Cup and 2019 FIFA Women’s World Cup.

Fig. 9 Scatterplot of the relationship between age (in years) and goals scored (log(x + 1) transformed) compared across the 2018 FIFA World Cup and 2019 FIFA Women’s World Cup and accounting for differences in field position.