Why statistical tests validate hypotheses in R Programming - See It in Action

Why Statistical Tests Validate Hypotheses

📖 Scenario: Imagine you are a scientist testing if a new medicine changes blood pressure. You collect data from patients and want to check if the medicine really works or if the changes happened by chance.

🎯 Goal: You will write a simple R program that uses a statistical test to check if the average blood pressure after medicine is different from before. This helps you understand how statistical tests validate hypotheses.

📋 What You'll Learn

Create a numeric vector called before with exact values: 120, 122, 119, 130, 125

Create a numeric vector called after with exact values: 115, 118, 117, 128, 120

Create a variable called alpha and set it to 0.05

Use t.test() with before and after to perform a paired t-test

Print the p-value from the test result

💡 Why This Matters

🌍 Real World

Scientists and researchers use statistical tests to check if their ideas about data are true or just random chance.

💼 Career

Understanding hypothesis testing is important for data analysts, scientists, and anyone working with data to make informed decisions.

1

Create the blood pressure data vectors

Create a numeric vector called before with values 120, 122, 119, 130, 125 and another numeric vector called after with values 115, 118, 117, 128, 120.

R Programming

# Create vectors before and after with given values
# Your code here

Need a hint?

Use the c() function to create numeric vectors with the exact numbers.

2

Set the significance level

Create a variable called alpha and set it to 0.05 to represent the significance level for the test.

R Programming

before <- c(120, 122, 119, 130, 125)
after <- c(115, 118, 117, 128, 120)
# Create alpha and set it to 0.05
# Your code here

Need a hint?

Just assign 0.05 to a variable named alpha.

3

Perform the paired t-test

Use the t.test() function with before and after vectors to perform a paired t-test. Save the result in a variable called test_result.

R Programming

before <- c(120, 122, 119, 130, 125)
after <- c(115, 118, 117, 128, 120)
alpha <- 0.05
# Perform paired t-test and save to test_result
# Your code here

Need a hint?

Use t.test(before, after, paired = TRUE) to compare paired samples.

4

Print the p-value from the test

Print the p-value from test_result using print(test_result$p.value).

R Programming

before <- c(120, 122, 119, 130, 125)
after <- c(115, 118, 117, 128, 120)
alpha <- 0.05
test_result <- t.test(before, after, paired = TRUE)
# Print the p-value
# Your code here

Need a hint?

Use print(test_result$p.value) to show the p-value. The exact output will be close to 0.0027.