p comments on multiple regression output summary the

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

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: .364 0.7157 -0.290 0.7723 2.368 0.0182 * 0.05 ’.’ 0.1 ’ ’ 1 Resid. stand. error: 16.43 on 693 degr. of freedom Multiple R-squared: 0.2117, Adj. R-squared: 0.2038 F-stat.: 26.59 on 7 and 693 DF, p-value: < 2.2e-16 27 Multiple Regression Decomposition and R 2 Via matrix algebra one gets again the following decomposition n n (yi − y )2 = ¯ SYY = i =1 n (yi − yi )2 + ˆ i =1 (ˆi − y )2 = RSS + SSreg y ¯ i =1 where the tted values are ˆ ˆ ˆ yi = β0 + β1 xi 1 + . . . + βp xip ˆ The multiple correlation coecient is R2 = SSreg SYY − RSS RSS = =1− SYY SYY SYY with adjusted p+1 28 ¯ R 2 = R 2 = 1 − is the number of tted parameters n−1 (1 − R 2 ) n−p−1 β0 , . . . , β p . Comments on Multiple Regression Output Summary The Std. Error is the estimated standard deviation of the respective estimate. The t value is the ratio t = Estimate/Std. Pr( > |t|) represents the two-sided p-value for the observed value t, Error. The when testing the hypothesis F statistic tests the hypothesis H0 : β1 = . . . = βp = 0. Hj : βj = 0. of no regression eect at all, i.e., It appears that the intercept ht β0 = 0 and that are signicant predictor variables, i.e., The signicance of dwt should be viewed with caution, in the context of multiple tests performed. 29 gestation and β1 = 0 and β3 = 0. Model Update We delete the non-signicant variables from previous analysis > wtreg0 <- update(wtreg,.~.-age-wt1-dage-dht) > summary(wtreg0) Call: lm(formula = wt ~ gestation + ht + dwt, data = babies, subset = gestation < 999 & age < 99 & ht < 99 & wt1 < 999 & dage < 99 & dht < 99 & dwt < 999) Residuals: Min 1Q -48.230 -10.482 Median 0.394 Note the modied model call. 30 3Q 10.379 Max 56.108 Model Update (Output Continued) Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) -102.46196 18.91277 -5.418 8.33e-08 gestation 0.44803 0.03893 11.509 < 2e-16 ht 1.31132 0.25456 5.151 3.37e-07 dwt 0.07553 0.02839 2.660 0.00799 --Signif. codes: 0 ’***’ 0.001 ’**’ 0.01 ’*’ 0.05 ’.’ 0.1 ’ ’ 1 Resid. std. error: 16.45 on 697 degrees of freedom Multiple R-squared: 0.2056, Adj. R-squared: 0.2021 F-stat.: 60.12 on 3 and 697 DF, p-value: < 2.2e-16 31 * * * * Examining Normality of Residuals > qqnorm(wtreg0$resid) > qqline(wtreg0$resid) 60 Normal Q−Q Plot q q q q q 20 0 −40 −20 Sample Quantiles 40 q q q qq q q q q q qq qq qq qq qq q q qq qq qqq qqq qqq qq q q qq q q q qq qq qq qq qq q q q q qq q q q q qq q q q q q q q q q q q qq q qq qq q qq qq qq q q qq qq qq qq qq qq qq qq qq q q qq qq qq qq qq q q q qq qq qq qq qq qq q q qq q qq q q q qq qq qq qq qq qq qqq qq qq qqq qqq qq qq qq qq qq qq q qq qq qq qq qq qq qq qq q qq qq qq qq q q q q q qq qq qq qq qq qq q qq qq q qq qq qq qq qq qq qq qq qq qq qq qq qq qq qq qq qq qq qq qq qq qq qq qq qq qq qq q q qq qq qq q q qq qq qq qq q qq q qq qq q q q q qq qqq qqq qqq qq qq q q q q q q q q q q q qq q q q qq q q q q q q q q q q q qqq qqq qqq qqq qq qq qq qqq qq q qq q qq qq q q q q q qqq q q q q −3 −2 −1 0 Theoretical Quantiles 32 1 2 3...
View Full Document

Ask a homework question - tutors are online