Chapter 13.5, Problem 57E

In the accompanying table, we give the smallest SSE for each number of predictors k (k = 1, 2, 3, 4) for a regression problem in which y = cumulative heat of hardening in cement, x₁ = % tricalcium aluminate, x₂ = % tricalcium silicate, x₃ = % aluminum ferrate, and x₄ = % dicalcium silicate.

Number of Predictors k	Predictor(s)	SSE
1	x4	880.85
2	x1,x2	58.01
3	x1,x2,x3	49.20
4	x1, x2,x3,x4	47.86

In addition, n = 13 and SST = 2715.76.

a.    Use the criteria discussed in the text to recommend the use of a particular regression model.

b.    Would forward selection result in the best twopredictor model? Explain.