Classic Fransis Galton heights of fathers and sons data set and the simple regression

R codes to get the data and run the regression

father.son<-read.table(“http://stat-www.berkeley.edu/users/juliab/141C/pearson.dat”,sep=” “)[,-1]
names(father.son)[2]<-“hson”
names(father.son)[1]<-“hfather”
head(father.son)
plot(hson ~ hfather, data=father.son, bty=”l”, pch=20)
abline(a=0,b=1,lty=2,lwd=2) # what is the hypothesis here? Why we are looking at this line
abline(lm(hson ~ hfather, data=father.son),lty=1,lwd=2) # what is the hypotheses here? which one to use – this or the previous one?

The outputs are:

Call:
lm(formula = hson ~ hfather, data = father.son)

Coefficients:
(Intercept)      hfather
33.8866       0.5141

The graphical output is

One thought on “Classic Fransis Galton heights of fathers and sons data set and the simple regression

  1. Pingback: A way to achieve Excellence in Teaching – Make it Simple, Fun, Learning | BIG Data, Data Mining, Predictive Modeling, and Visualizations – Welcome

Leave a Reply

Your email address will not be published. Required fields are marked *