Randomization
Randomization of subjects in an experiment helps spread any variability that exists naturally between subjects evenly across groups. For ToothGrowth, an example of effective randomization would be randomly assigning male and female guinea pigs into different experimental groups, ideally canceling out any existing differences that naturally exist between male and female guinea pigs.
In the experiment that yielded the ToothGrowth
dataset, guinea pigs were randomized to receive Vitamin C either through orange juice or ascorbic acid, indicated in the dataset by the supp
variable. It's natural to wonder if there is a difference in tooth length by supplement type - a question that a t-test can also answer!
Starting with this exercise, you should use t.test()
and other modeling functions with formula notation:
t.test(outcome ~ explanatory_variable, data = dataset)
This can be read: "test outcome
by explanatory_variable
in my dataset
." The default test for t.test()
is a two-sided t-test.
This exercise is part of the course
Experimental Design in R
Exercise instructions
- Conduct a t-test to determine if there is a difference in tooth length (
len
) based on supplement type (supp
), and save the results as an objectToothGrowth_ttest
. - Load the
broom
package. - Tidy the
ToothGrowth_ttest
withtidy()
. This will print the results to the console.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Perform a t-test
___ <- t.test(___, data = ToothGrowth)
# Load broom
library(___)
# Tidy ToothGrowth_ttest
___