The First Pitch Effect

first.pitch.effects.R

##########################################
# the first pitch effect
# preview of Chapter 7 material in ABDWR
##########################################

# load in Retrosheet 2013 play-by-play data
# (have to download Retrosheet data and add run values)

load("pbp2013.Rdata")

# restrict attention to batting plays

d2013 <- subset(d2013, BAT_EVENT_FL==TRUE)

# remove pickoff throws, etc from pitch sequence variable

d2013$pseq <- gsub("[.>123N+*]", "", d2013$PITCH_SEQ_TX)

# First.Pitch variable records outcome of first pitch

d2013$First.Pitch <- substr(d2013$pseq, 1, 1)

# Count variable records if the first pitch count is 0-1, 1-0 or
# the plate appearance is over (hit by pitch or ball hit in play)

d2013$Count <- ifelse(d2013$First.Pitch %in% 
        c("C", "F", "L", "M", "O", "Q", "S", "T"),
        "0-1", ifelse(d2013$First.Pitch %in% c("B", "I", "P"),
        "1-0", "End.PA"))

# find sample size, mean, and sd of run values for 
# the plate appearances for each possibility (0-1, 1-0, or End.PA)

with(d2013, c(N=length(RUNS.VALUE), 
              Mean=mean(RUNS.VALUE), 
              SD=sd(RUNS.VALUE)))
     
library(dplyr)
S <- summarize(group_by(d2013, Count),
          N=length(RUNS.VALUE), 
          Mean=mean(RUNS.VALUE), 
          SD=sd(RUNS.VALUE))
S
# graph error bars of the run values for each 
# first pitch outcome

library(ggplot2)
limits <- aes(ymin=Mean - SD, ymax=Mean + SD)
ggplot(S, aes(Count, Mean)) + 
  geom_point(size=6, color="red") +
  geom_pointrange(limits, color="red", size=1.5) +
  geom_hline(xintercept=0, color="blue") + 
  labs(title="The First Pitch Effect")+
  ylab("Run Value") +
  xlab("Outcome of First Pitch") +
  theme(axis.text = element_text(size = rel(2))) +
  theme(axis.title = element_text(size = rel(2))) +
  theme(plot.title = element_text(size = rel(2))) 

##################################################