Galton parent/child frequency plot

freqplot-galton.R

library(HistData)
galton <- Galton

y <- galton$child
x <- galton$parent
freqData <- as.data.frame(table(galton$child, galton$parent))
names(freqData) <- c("child", "parent", "freq")
plot(as.numeric(as.vector(freqData$parent)), 
     as.numeric(as.vector(freqData$child)), 
     pch = 21, col = "black", bg = "lightblue",
     cex = .07 * freqData$freq, xlab = "parent", ylab = "child")

#original regression line, children as outcome, parents as predictor
abline(mean(y) - mean(x) * cor(y, x) * sd(y) / sd(x), #intercept
       sd(y) / sd(x) * cor(y, x),  #slope
       lwd = 3, col = "red")

#new regression line, parents as outcome, children as predictor
abline(mean(y) - mean(x) * sd(y) / sd(x) / cor(y, x), #intercept
       sd(y) / cor(y, x) / sd(x), #slope
       lwd = 3, col = "blue")

#assume correlation is 1 so slope is ratio of std deviations
abline(mean(y) - mean(x) * sd(y) / sd(x), #intercept
       sd(y) / sd(x),  #slope
       lwd = 2)
points(mean(x), mean(y), cex = 2, pch = 19) #big point of intersection