{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

Lec12.MultiDiag

# Lec12.MultiDiag - MultipleRegression Diagnostics...

This preview shows pages 1–14. Sign up to view the full content.

Click to edit Master subtitle style Multiple Regression  Diagnostics KNNL Chapter 10 (10.1-10.3,10.5) Building the Regression Model II Lec12.MultiDiag.ssc

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Multicolinearity: KNNL Chapters 7.6, 10.5 Comments section also Adding or deleting a predictor variable changes  the regression coefficients Estimated standard deviations of coefficients  become large  Coefficients may not be statistically significant Make sure to read …
alligator\$Length 60 80 100 120 140 100 200 300 400 500 600 alligator\$Weight Alligator Polynomial Model

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
F-Statistic: Kutner et al. pg 73
anova(alligator2.lm, alligator3.lm, test = "F") Analysis of Variance Table Response: Weight                          Terms Resid.Df Resid.Dev           1            Length + Length^2        21 5267.637                                                 2 Length + Length^2 + Length^3        20 2684.465  Test  Df Sum of Sq F Value        Pr(F) +I(Length^3) 1 2583.172 19.24534 0.0002847591 0 : hypothesis null Test 3 = β

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
anova(alligator3.lm, alligator4.lm, test = "F") Analysis of Variance Table Response: Weight Terms  Resid. Df Resid. Dev          1 Length + Length^2 + Length^3     20   2684.465                                               2 Length + Length^2 + Length^3 + Length^4                                            19   2581.174 Test    Df Sum of Sq F Value     Pr(F) +I(Length^4)  1  103.2905 0.7603201 0.3941139  0 : hypothesis null Test 4 = β
( 29 - - = = 2 1 2 2 2 2 ) ( exp ) 2 ( 1 ; σ θ πσ θ n i i n x L x The Normal Likelihood Function Obj105

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
2 2 2 2 ) ( ) 2 ln( 2 ln σ θ πσ - + = - i x n L The Negative Log Likelihood 2 ) ( ln σ θ θ - - = - i x L d d 2 2 2 ln σ θ n L d d = - Hessian Matrix
Akaike Information Criteria (AIC) Schwarz’ Bayesian Criteria (SBC,  AIC = n*log(SSE) - n*log(n) + 2*p SBC = n*log(SSE) - n*log(n) + log(n)*p Kutner et al. Notation

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
# Splus/R AIC # -2*log-likelihood + 2*npar # where npar includes coefficients and sigma2 sum(resid(alligator3.lm)^2) 2684.465 SSE = sum(resid(alligator3.lm)^2) p = length(coef(alligator3.lm)) n = length(resid(alligator3.lm))
lm1=lm(Weight~Length,data=alligator) text(1,AIC(lm1),1) lm1=lm(Weight~Length^2,data=alligator) text(1,AIC(lm1),2) lm1=lm(Weight~Length^3,data=alligator) text(1,AIC(lm1),3) lm1=lm(Weight~Length^4,data=alligator) text(1,AIC(lm1),4) One at a time

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Number of Parameters 0 1 2 3 4 5 6 100 150 200 250 300 350 AIC 1 2 3 4 AIC Plot: Single Variable Models
lm1=lm(Weight~Length+Length^2,data=alligator) AIC.p = rbind(AIC.p,c(3,AIC(lm1),12)) lm1=lm(Weight~Length+Length^3,data=alligator) AIC.p = rbind(AIC.p,c(3,AIC(lm1),13)) lm1=lm(Weight~Length+Length^4,data=alligator) AIC.p = rbind(AIC.p,c(3,AIC(lm1),14)) lm1=lm(Weight~Length^2+Length^3,data=alligator) AIC.p = rbind(AIC.p,c(3,AIC(lm1),23))

This preview has intentionally blurred sections. Sign up to view the full version.

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

{[ snackBarMessage ]}