S4. Null Hypothesis Significance Testing & Type I and II errors

Questions to ask about sample mean

Does the sample mean look very different from the population average? Does the sample mean look inconsistent with the sample of the appropriate size from this population?

Null Hypothesis Significance Testing

1. Hypothesis (H1 & H0). 2. Data. 3. Evaluate inconsistency with H0. 4. Reject or fail to reject. (p < 0.05) 5. Interpret

Z-test

use Z-score to do step 1&2 of NHST. To evaluate inconsistency, use z-score table to see if p < 0.05, to see whether H0 should be rejected or fail to be rejected.

1 tailed hypothesis testing

testing for a hypothesis with a stated difference, look at z-score table at either above or below depending on hypothesis.

2 tailed hypothesis testing

testing for a hypothesis with an unstated difference. p = z-score x 2 < 0.05

Type I error

rejecting the NULL when it was correct.

Type 2 error

failing to reject the NULL when it was incorrect.