1
Regression Homework Solutions
EPP 245/298
Statistical Analysis of
Laboratory Data
October 27, 2004 EPP 245 Statistical Analysis of Laboratory Data
2
Exercise 5.1
> library(ISwR)> data(rmr)> attach(rmr)> names(rmr)[1] "body.weight" "metabolic.rate"> plot(body.weight,metabolic.rate)> rmr.lm <- lm(metabolic.rate ~ body.weight)> abline(coef(rmr.lm),col="red",lwd=2)
October 27, 2004 EPP 245 Statistical Analysis of Laboratory Data
3
October 27, 2004 EPP 245 Statistical Analysis of Laboratory Data
4
> coef(rmr.lm)(Intercept) body.weight 811.226674 7.059528 > 811.226674 + 7.059528*70[1] 1305.394> sum(coef(rmr.lm)*c(1,70))[1] 1305.394> predict(rmr.lm,data.frame(body.weight=70))[1] 1305.394
October 27, 2004 EPP 245 Statistical Analysis of Laboratory Data
5
> summary(rmr.lm)
Call:lm(formula = metabolic.rate ~ body.weight)
Residuals: Min 1Q Median 3Q Max -245.74 -113.99 -32.05 104.96 484.81
Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) 811.2267 76.9755 10.539 2.29e-13 ***body.weight 7.0595 0.9776 7.221 7.03e-09 ***---Signif. codes: 0 `***' 0.001 `**' 0.01 `*' 0.05 `.' 0.1 ` ' 1
Residual standard error: 157.9 on 42 degrees of freedomMultiple R-Squared: 0.5539, Adjusted R-squared: 0.5433 F-statistic: 52.15 on 1 and 42 DF, p-value: 7.025e-09
October 27, 2004 EPP 245 Statistical Analysis of Laboratory Data
6
Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) 811.2267 76.9755 10.539 2.29e-13 ***body.weight 7.0595 0.9776 7.221 7.03e-09 ***
> 7.0595 - 1.96*0.9776[1] 5.143404> 7.0595 + 1.96*0.9776[1] 8.975596> tmp <- summary(rmr.lm)> names(tmp) [1] "call" "terms" "residuals" "coefficients" [5] "aliased" "sigma" "df" "r.squared" [9] "adj.r.squared" "fstatistic" "cov.unscaled" > tmp$coef Estimate Std. Error t value Pr(>|t|)(Intercept) 811.226674 76.9755034 10.53876 2.288384e-13body.weight 7.059528 0.9775978 7.22130 7.025380e-09> class(tmp$coef)[1] "matrix"> dim(tmp$coef)[1] 2 4
October 27, 2004 EPP 245 Statistical Analysis of Laboratory Data
7
Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) 811.2267 76.9755 10.539 2.29e-13 ***body.weight 7.0595 0.9776 7.221 7.03e-09 ***
> 7.0595 - 1.96*0.9776[1] 5.143404> 7.0595 + 1.96*0.9776[1] 8.975596> tmp$coef[2,1] - 1.96*tmp$coef[2,2][1] 5.143436> tmp$coef[2,1] + 1.96*tmp$coef[2,2][1] 8.97562
October 27, 2004 EPP 245 Statistical Analysis of Laboratory Data
8
Exercise 5.2> data(juul)> names(juul)[1] "age" "menarche" "sex" "igf1" "tanner" "testvol" > attach(juul)> juul.lm <- lm(sqrt(igf1) ~ age, sub=(age>25))> summary(juul.lm)
Call:lm(formula = sqrt(igf1) ~ age, subset = (age > 25))
Residuals: Min 1Q Median 3Q Max -4.8642 -1.1661 0.1018 0.9450 4.1136
Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) 18.71025 0.49462 37.828 <2e-16 ***age -0.10533 0.01072 -9.829 <2e-16 ***---Signif. codes: 0 `***' 0.001 `**' 0.01 `*' 0.05 `.' 0.1 ` ' 1
Residual standard error: 1.741 on 120 degrees of freedomMultiple R-Squared: 0.446, Adjusted R-squared: 0.4414 F-statistic: 96.6 on 1 and 120 DF, p-value: < 2.2e-16
October 27, 2004 EPP 245 Statistical Analysis of Laboratory Data
9
October 27, 2004 EPP 245 Statistical Analysis of Laboratory Data
10
> plot(age,igf1)> plot(age[age>25],igf1[age>25])> abline(coef(lm(igf1 ~ age,sub=(age>25))),col="red",lwd=2)> plot(age[age>25],sqrt(igf1)[age>25])> abline(coef(juul.lm),col="red",lwd=2)
October 27, 2004 EPP 245 Statistical Analysis of Laboratory Data
11
October 27, 2004 EPP 245 Statistical Analysis of Laboratory Data
12
October 27, 2004 EPP 245 Statistical Analysis of Laboratory Data
13
October 27, 2004 EPP 245 Statistical Analysis of Laboratory Data
14
October 27, 2004 EPP 245 Statistical Analysis of Laboratory Data
15
> data(malaria)> > names(malaria)[1] "subject" "age" "ab" "mal" > attach(malaria)> hist(ab)> hist(log(ab))> plot(age,log(ab))> summary(lm(log(ab) ~ age))
Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) 3.83697 0.38021 10.092 <2e-16 ***age 0.10350 0.03954 2.618 0.0103 * ---Signif. codes: 0 `***' 0.001 `**' 0.01 `*' 0.05 `.' 0.1 ` ' 1
Residual standard error: 1.478 on 98 degrees of freedomMultiple R-Squared: 0.06536, Adjusted R-squared: 0.05582 F-statistic: 6.853 on 1 and 98 DF, p-value: 0.01025
Exercise 5.3
October 27, 2004 EPP 245 Statistical Analysis of Laboratory Data
16
October 27, 2004 EPP 245 Statistical Analysis of Laboratory Data
17
October 27, 2004 EPP 245 Statistical Analysis of Laboratory Data
18
October 27, 2004 EPP 245 Statistical Analysis of Laboratory Data
19