Correlation

Read data;  plot data;  calculate correlation

1) Read data

Download example of dataset saved as tab separated text file .tsv

# read dataset (tabulator \t separated text file)

mydata = read.table('Downloads/data_2x20.tsv', sep="\t", header=TRUE)

# check dataset 'mydata'

head(mydata)    # show top lines of dataset

          height width

sample01  6.576 3.644

sample02  6.379 3.110

sample03 10.542 4.213

sample04  4.543 2.954

sample05  6.092 3.248

sample06  8.804 3.907

dim(mydata)  # get size of dataset (20 lines, 2 columns)

[1] 20  2

2) Plot height vs. width

plot(height ~ width, data = mydata, cex = 1.5,  pch = 21, bg = 'blue')

   # plot circles 1.5 times bigger;  filled circles (code:21);  in blue color

3) Calculate correlation

cor( mydata$height , mydata$width )

[1] 0.9304076

Result: 'height' and 'width' are highly correlated (Pearson correlation=0.93).