［R］MLBにおける2001～2010年の得点差分と勝率の散布図（「Rによるセイバーメトリクス入門」（技術評論社）pp.95-99）

> library(tidyverse)
> library(Lahman)
> my_teams <- Teams %>% filter(yearID > 2000 & yearID < 2011) %>%
+ select(teamID, yearID, lgID, G, W, L, R, RA)
> my_teams %>% tail()
    teamID yearID lgID   G  W  L   R  RA
295    SFN   2010   NL 162 92 70 697 583
296    SLN   2010   NL 162 86 76 736 641
297    TBA   2010   AL 162 96 66 802 649
298    TEX   2010   AL 162 90 72 787 687
299    TOR   2010   AL 162 85 77 755 728
300    WAS   2010   NL 162 69 93 655 742
> my_teams <- my_teams %>% mutate(RD = R - RA, Wpct = W / (W + L))
> run_diff <- ggplot(my_teams, aes(x = RD, y = Wpct)) + geom_point() +
+ scale_x_continuous("Run differential") +
+ scale_y_continuous("Winning percentage")
> print(run_diff)
> crcblue <- "#2905A1"
> linfit <- lm(Wpct ~ RD, data = my_teams)
> print(linfit)
Call:
lm(formula = Wpct ~ RD, data = my_teams)
Coefficients:
(Intercept)           RD  
  0.4999909    0.0006216  
> run_diff + geom_smooth(method = "lm", se = FALSE, color = crcblue)
`geom_smooth()` using formula = 'y ~ x'