Unformatted text preview: >summary(lm(y˜x)) Coefficients: Estimate Std. Error t value Pr(>t) (Intercept) 0.66 0.16 4.00 0.016 x 0.12 0.003 41.24 2.07e06 Multiple RSquared: 0.9977 Example 2. Suppose that data ( x j , y j ) satisfy a circular relationship Y j = q 10 2x 2 j + ± j . This is a nonlinear relationship so we expect not to have a good linear fit. 30 40 50 60 70 80 5 6 7 8 9 10 x y Figure 1: Hooke’s law.105 5 10 2 4 x Figure 2: Complete lack of linear fit. >x<10:10 >y<sqrt(10ˆ2 xˆ2) >summary(lm(y˜x)) Coefficients: value Pr(>t) (Intercept) . ... 1.24e09 x .... 4.47e17 Multiple RSquared: 1.378e030 Selfstudy problems Construct 100(1α )% confidence intervals for both β and β 1 . Show Var ( ˆ β ) = σ 2 x 2 /S xx . Example 12.9....
View
Full Document
 Spring '04
 Chung
 Statistics, Coefficient Of Determination, Normal Distribution, Regression Analysis, Variance, Pearson productmoment correlation coefficient, SST

Click to edit the document details