This preview shows pages 1–3. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: Rebecca Nugent, Department of Statistics, Carnegie Mellon University, 2011 2 Comparing Distributions: boxplots need to be on same y-axis; can put two graphs next to each other with the same y-range OR can put two boxplots in the same graphics window What do we look for? par(mfrow=c(2,1)) boxplot(fat[shelf==1],fat[shelf==2],fat[shelf==3],names=c("Shelf 1","Shelf 2", "Shelf 3"),ylab="Fat in Grams per Portion") title("Fat Content by Shelf Location") boxplot(fat~mfr,ylab="Fat in Grams per Portion") title("Fat Content by Manufacturer") Boxplot Advantages? Disadvantages? Box-Percentile Plot: combining quartiles with features of a cumulative distribution function library(Hmisc); par(mfrow=c(1,2)) x<-c(runif(50,-1,1),runif(50,1.1,1.15),runif(100,1.3,3.3)) boxplot(x,col=2,main="Trimodal: Boxplot") bpplot(x,main="Trimodal: Box-Percentile Plot") Rebecca Nugent, Department of Statistics, Carnegie Mellon University, 2011 3...
View Full Document
This note was uploaded on 04/15/2011 for the course STATISTICS 315 taught by Professor Gnt during the Spring '11 term at Carnegie Mellon.
- Spring '11