Texts: The pollution of a city is caused by the industrial waste and the carbon monoxide emitted by its huge traffic, which has no smoke check standards. The levels of the pollution (y), the industrial waste (x1), and the carbon monoxide (x2) measured from six locations in the city are given in:
i) Fit the data to a regression equation using 3-fold cross-validation.
a) The regression equation is:
b) The cross-validation error is:
ii) Fit the data to a regression equation using 2-fold cross-validation.
a) The regression equation is:
b) The cross-validation error is:
iii) Fit the data to a regression equation using leave-one-out cross-validation.
a) The regression equation is:
b) The cross-validation error is:
iv) Based on the mean square error, what is the best model?
Data:
waste <- data.frame(y = c(29.2, 34, 30, 33, 36, 38), x1 = c(30.2, 20.5, 25.5, 35.7, 30.6, 27.5), x2 = c(7.2, 9.5, 8.2, 7.4, 8.4, 9.5))