Type I error vs Type II error
How to tell Type I error and Type II error apart when a board question makes them look alike.
Type I error (alpha): false positive, rejecting a true null; type II error (beta): false negative, missing a real effect.
Side by side
Type I error is a false positive conclusion, rejecting a true null hypothesis, with probability alpha.
Type II error is a false negative conclusion, failing to reject a false null hypothesis, with probability beta and related to power.
Type I error is a false positive conclusion, rejecting a true null hypothesis, with probability alpha.
Type II error is a false negative conclusion, failing to reject a false null hypothesis, with probability beta and related to power.
Alpha is the preset significance threshold, usually 0.05; a p-value below alpha rejects the null, so a false positive is a Type I error.
Beta is the false negative rate; power equals 1 minus beta and rises with a larger sample size, a larger effect size, or less variability.
The trap
Type I is false positive alpha; Type II is false negative beta.
Watch it explained
Test it nowThe repair move
Before naming the answer, force the stem through the separator: Type I is false positive alpha; Type II is false negative beta.
Try a free question
CoreA clinical trial of a new antihypertensive drug compares it to placebo. The null hypothesis is that the drug has no effect on blood pressure. The trial reports p = 0.03 in favor of the drug, and the researchers reject the null hypothesis. However, in truth, the drug has no real effect on blood pressure. Which error has occurred?
Show answer and explanation
Answer: A. Type I error (false positive). Type I error (alpha, false positive) = rejecting the null hypothesis when it is actually true. Conventional acceptable rate is alpha = 0.05 (5% chance of falsely concluding a treatment works). This is the FALSE ALARM. Lowering alpha (e.g., 0.01) reduces type I error but increases type II error.
Why the other choices are tempting
- B. Type II error is FAILING to reject a false null (false negative; missed real effect).
- C. Sampling error is general variability from sampling.
- D. Random allocation error is incorrect group assignment.
- E. Effect size error isn't a defined statistical term.
Flashcards
Tap a card to flip it.
What clue supports Type I error?
Choose Type I error when the stem gives this pattern: Type I error is a false positive conclusion, rejecting a true null hypothesis, with probability alpha.
What clue supports Type II error?
Choose Type II error when the stem gives this contrasting pattern: Type II error is a false negative conclusion, failing to reject a false null hypothesis, with probability beta and related to power.
Quick answers
What is the fastest way to tell Type I error from Type II error?
Type I error (alpha): false positive, rejecting a true null; type II error (beta): false negative, missing a real effect.
What is the key clue for Type I error?
Type I error is a false positive conclusion, rejecting a true null hypothesis, with probability alpha.
What is the key clue for Type II error?
Type II error is a false negative conclusion, failing to reject a false null hypothesis, with probability beta and related to power.
What is the common trap with Type I error vs Type II error?
Type I is false positive alpha; Type II is false negative beta.