Lecture 1: Introduction into R data analysis

First, import some data into a data structure using the READ command.

options(repr.plot.width=10, repr.plot.height=6.5)   # this command just formats the size of the figures. Adapt to view them nicely
                                                    # in your browser.

mydatastructure = read.csv("YieldStrengthData.csv")  # read csv file 
mydata = mydatastructure$YieldStrength

mydatastructure

A data.frame: 23 × 1

YieldStrength
<dbl>
12.0
11.8
14.2
10.5
12.3
15.4
9.8
11.1
13.4
12.5
11.4
10.8
1.2
14.8
15.0
13.5
14.1
11.2
11.2
13.5
12.3
12.1
11.6

plot(mydata,rep(0,length(mydata)),     # plot(x,y)    ; command rep = repeat. 
     xlab="Yield Strength (MPa)",
     ylab=" ",
     col="blue"
     )

Histograms

hist(mydata,
     breaks = seq(floor(min(mydata)),ceiling(max(mydata)),by=1),
     plot=TRUE, 
     axes=TRUE, 
     xlab="Yield Strength (MPa)",
     col="orange",
     freq=TRUE)

Empirical Cumulative Distribution Function (ECDF)

plot(ecdf(mydata))

Mean vs. Median

plot(mydata,rep(0,length(mydata)),     # plot(x,y)    ; command rep = repeat. 
     xlab="Yield Strength (MPa)",
     ylab=" ",
     col="blue"
     )
abline(v=mean(mydata), col="red",lwd=3)
mtext(paste("mean=", signif(mean(mydata),4)),col="red")
abline(v=median(mydata), col="blue",lwd=3)
mtext(paste("median=", signif(median(mydata),4)),col="blue",adj = 0)

# some random data
mydata <- rnorm(n =  1000,mean = 13,sd = 9)

# bipartite data
mydata <- c(rnorm(50,10,3),rnorm(5,300,0.3))

# asymmetric data
mydata <- c(rnorm(300,20,5),rnorm(150,40,10))

Quantiles

quantile(mydata, probs = c(0,0.1,0.3,0.4,0.5,0.75,1))

0%

6.12653045617659

10%

14.1905778794507

30%

18.9941605578449

40%

21.0653916427957

50%

23.5398728734673

75%

32.2687110060274

100%

67.4131892810316

Our first Boxplot

boxplot(mydata)