Statistics Homework Solutions 197

Statistics Homework Solutions 197 - (c) 500 1000 1500...

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
SECTION 8.3 197 (e) The F -test cannot be used. The F -test can only be used when one model is formed by dropping one or more independent variables from another model. (f) The predictions of the two models do not differ much. The log model has only one independent variable instead of two, which is an advantage. 13. (a) Predictor Coef StDev T P Constant 37.989 53.502 0.71004 0.487 x 1.0774 0.041608 25.894 0.000 (b) Predictor Coef StDev T P Constant 253 45 132.93 1 9067 0.074 x 1.592 0.22215 7.1665 0.000 x 2 0 00020052 0.000085328 2 3499 0.031
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: (c) 500 1000 1500 2000-150-100-50 50 100 150 200 Fitted Value Residual Linear Model (d) 500 1000 1500 2000 2500-150-100-50 50 100 150 Fitted Value Quadratic Model (e) The quadratic model seems more appropriate. The P-value for the quadratic term is fairly small (0.031), and the residual plot for the quadratic model exhibits less pattern. (There are a couple of points somewhat detached from the rest of the plot, however.)...
View Full Document

This note was uploaded on 12/20/2011 for the course STA 3163 taught by Professor Mattgilg during the Fall '11 term at UNF.

Ask a homework question - tutors are online