Key Differences Between Type I & Type II Errors
| Error Type | What Happens? | Example |
|---|---|---|
| Type I Error (False Positive) | Rejecting a true null hypothesis (finding an effect when there is none) | A fire alarm rings, but there’s no fire. |
| Type II Error (False Negative) | Failing to reject a false null hypothesis (missing an actual effect) | A fire is burning, but the alarm does not ring. |
| Scenario | Reality: Person is Healthy | Reality: Person is Infected |
|---|---|---|
| Test Result: Positive | Type I Error (False Positive) – A healthy person is wrongly diagnosed with COVID-19. | ✅ Correct – Infected person is correctly diagnosed. |
| Test Result: Negative | ✅ Correct – Healthy person is correctly diagnosed. | Type II Error (False Negative) – An infected person is wrongly told they don’t have COVID-19. |
How to Reduce These Errors?
-
To reduce Type I Error, lower α (significance level) (e.g., from 5% to 1%).
-
To reduce Type II Error, increase sample size or improve testing accuracy.