Something to do in preparation of class discussion on Monday … 

#
# Anscombe quartet – 
#

# data set 1
ds1<- data.frame(scan(what=list(x=0,y=0)))
10.0 8.04 8.0 6.95 13.0 7.58 9.0 8.81 11.0 8.33 14.0 9.96
6.0 7.24 4.0 4.26 12.0 10.84 7.0 4.82 5.0 5.68

# data set 2
ds2<- data.frame(scan(what=list(x=0,y=0)))
10.0 9.14 8.0 8.14 13.0 8.74 9.0 8.77 11.0 9.26 14.0 8.10
6.0 6.13 4.0 3.10 12.0 9.13 7.0 7.26 5.0 4.74

# data set 3
ds3<- data.frame(scan(what=list(x=0,y=0)))
10.0 7.46 8.0 6.77 13.0 12.74 9.0 7.11 11.0 7.81 14.0 8.84
6.0 6.08 4.0 5.39 12.0 8.15 7.0 6.42 5.0 5.73

# data set 4
ds4<- data.frame(scan(what=list(x=0,y=0)))
8.0 6.58 8.0 5.76 8.0 7.71 8.0 8.84 8.0 8.47 8.0 7.04 8.0 
5.25 19.0 12.50 8.0 5.56 8.0 7.91 8.0 6.89

#
# fit the models
#
ds1.lmfit <- lm(y~x, data=ds1)
ds2.lmfit <- lm(y~x, data=ds2)
ds3.lmfit <- lm(y~x, data=ds3)
ds4.lmfit <- lm(y~x, data=ds4)

#
# fit summaries
#
summary(ds1.lmfit)
summary(ds2.lmfit)
summary(ds3.lmfit)
summary(ds4.lmfit)

TASK: Compare the prediction equations, hypothesis tests, anova table, R2, . . . from the fits of a linear model to these 4 data sets.

QUESTION: Are these all model fits all equally good?

We will discuss this on Monday . . .