Type II Error: False Negatives
What You'll Learn
You'll learn what a Type II error is, why it occurs, and how it's measured in hypothesis testing.
The Core Idea
In hypothesis testing, a Type II error occurs when we fail to reject the null hypothesis when it is actually false. In other words, we miss detecting a real effect or difference that truly exists.
Think of it like a medical test: a Type II error is when the test comes back negative for a disease that the patient actually has—a false negative. The treatment was needed, but we concluded it wasn't.
The Probability: β (Beta)
The probability of making a Type II error is denoted by the Greek letter β (beta). Unlike α (the Type I error rate, which we set in advance), β depends on several factors:
- The true parameter value: How far is reality from what the null hypothesis claims?
- Sample size: Larger samples make it easier to detect real effects (lower β)
- Significance level α: If you make α stricter (smaller), β typically increases
- Variability in the data: More noise makes real signals harder to detect
The Tradeoff
You've already learned about Type I errors (false positives with probability α). There's a fundamental tradeoff: reducing α often increases β, and vice versa. If you're very cautious about false alarms (low α), you become more likely to miss real effects (higher β).
The complement of β is called statistical power (1 - β)—the probability of correctly rejecting a false null hypothesis. Researchers typically aim for power of 0.80 or higher, meaning β ≤ 0.20.
Key Takeaway: Type II error (probability β) means failing to reject a false null hypothesis—missing a real effect that exists. It balances against Type I error in the design of hypothesis tests.