10.07.2015 Views

Multiple Linear Regression

Multiple Linear Regression

Multiple Linear Regression

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

-4.368 -1.670 -0.158 1.792 4.358Coefficients:Estimate Std. Error t value Pr(>|t|)(Intercept) -0.955101 63.013630 -0.015 0.988Girth -2.796569 1.468677 -1.904 0.068 .I(Girth^2) 0.265446 0.051689 5.135 2.35e-05 ***Height 0.119372 1.784588 0.067 0.947I(Height^2) 0.001717 0.011905 0.144 0.886---Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1Residual standard error: 2.674 on 26 degrees of freedom<strong>Multiple</strong> R-squared: 0.9771, Adjusted R-squared: 0.9735F-statistic: 277 on 4 and 26 DF, p-value: < 2.2e-16In this ill-formed model nothing is significant except Girth and Girth^2. Let us continuedown this path and suppose that we would like to try a reduced model which contains nothing butGirth and Girth^2 (not even an Intercept). Our two models are nowthe full model: Y = β 0 + β 1 x 1 + β 2 x 2 1 + β 3x 2 + β 4 x 2 2 + ɛ,the reduced model: Y = β 1 x 1 + β 2 x 2 1 + ɛ,We fit the reduced model with lm and store the results:> treesreduced.lm anova(treesreduced.lm, treesfull.lm)Analysis of Variance TableModel 1: Volume ~ -1 + Girth + I(Girth^2)Model 2: Volume ~ Girth + I(Girth^2) + Height + I(Height^2)Res.Df RSS Df Sum of Sq F Pr(>F)1 29 321.652 26 185.86 3 135.79 6.3319 0.002279 **26

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!