## Histogram of soccer player height (example 2.7 from Collaborative Stats)

# First, read in the data:

soccerheight= c( 60, 60.5, 61, 61, 61.5,
63.5, 63.5, 63.5,
64, 64, 64, 64, 64, 64, 64, 64.5, 64.5, 64.5, 64.5, 64.5, 64.5, 64.5, 64.5,
66, 66, 66, 66, 66, 66, 66, 66, 66, 66, 66.5, 66.5, 66.5, 66.5, 66.5, 66.5, 66.5, 66.5, 66.5, 66.5, 66.5, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67, 67.5, 67.5, 67.5, 67.5, 67.5, 67.5, 67.5,
68, 68, 69, 69, 69, 69, 69, 69, 69, 69, 69, 69, 69.5, 69.5, 69.5, 69.5, 69.5, 70, 70, 70, 70, 70, 70, 70.5, 70.5, 70.5, 71, 71, 71, 72, 72, 72, 72.5, 72.5, 73, 73.5, 74)

# Look at the summary (not part of the graphing procedure):

summary(soccerheight) 

# Make a histogram:

hist(soccerheight)

# Important but not new stuff first:

hist(soccerheight, main="Heights of Soccer Players", xlab="Height (inches)")

# Do those bins include the right end-points?

hist(soccerheight, main="Heights of Soccer Players", xlab="Height (inches)", right=TRUE)

hist(soccerheight, main="Heights of Soccer Players", xlab="Height (inches)", right=FALSE)

# How do we make the boundaries match the Collaborative Stats one?  First, make a list of the break points that we want:

boundaries = c(59.95, 61.95, 63.95, 65.95, 67.95, 69.95, 71.95, 73.95, 75.95)

# And then include them in the hist command via "breaks":

hist(soccerheight, main="Heights of Soccer Players", xlab="Height (inches)", right=FALSE, breaks=boundaries)

# If we want relative frequencies, set "freq" to FALSE.

hist(soccerheight, main="Heights of Soccer Players", xlab="Height (inches)", right=FALSE, breaks=boundaries, freq=FALSE)