SECTION 8.3
195
(d)
0
20
40
60
0
50
100
150
200
250
R
1
3
R
1
4
The correlation coefficient between
R
3
1
and
R
4
1
is 0.997.
(e)
R
3
1
and
R
4
1
are nearly collinear.
(f) The cubic model is best. The quadratic is inappropriate because the residual plot exhibits a pattern. The residual
plots for both the cubic and quartic models look good, however, there is no reason to include
R
4
1
in the model
since it merely confounds the effect of
R
3
1
.
Section 8.3
1. (a) False. There are usually several models that are about equally good.
(b) True.
(c) False. Model selection methods can suggest models that fit the data well.
This is the end of the preview.
Sign up
to
access the rest of the document.
 Fall '11
 MattGilg
 Statistics, Correlation, Quadratic equation, Harshad number, Cubic function, Quartic function, Degree of a polynomial, Large Pvalues

Click to edit the document details