two sample t-test

Paired Data

A dataset about book prices at two different stores, the UCLA bookstore and on Amazon. The prices at the two stores are paired on each book (specifically the ISBN number).

books <- read.csv("https://raw.githubusercontent.com/roualdes/data/master/books.csv")

For paired data, first create a new variable of the difference. Note which way the subtraction goes.

books$diff <- books$uclaNew - books$amazNew

With the new variable, we just perform a one sample t-test.

t.test(books$diff, mu = 0, conf.level = 0.9)

    One Sample t-test

data:  books$diff
t = 7.6488, df = 72, p-value = 6.928e-11
alternative hypothesis: true mean is not equal to 0
90 percent confidence interval:
  9.981505 15.541783
sample estimates:
mean of x 
 12.76164 

Two Sample t-test

Next, we’ll compare two numeric variables which are not paired.

suppressMessages(library(ape))
data(carnivora)

The variable longevity (LY) is measured in months.

t.test(LY ~ SuperFamily, data = carnivora, conf.level = 0.95)

    Welch Two Sample t-test

data:  LY by SuperFamily
t = 1.0243, df = 37.394, p-value = 0.3123
alternative hypothesis: true difference in means between group Caniformia and group Feliformia is not equal to 0
95 percent confidence interval:
 -20.03687  61.03354
sample estimates:
mean in group Caniformia mean in group Feliformia 
                192.4583                 171.9600