PSY 250 Lecture Notes - Lecture 19: Null Hypothesis, Statistical Hypothesis Testing, Interval Ratio
Document Summary
We get data from samples and not populations. But there is some amount of sampling error with each sample. This relationship exists in the population, and the relationship in my sample reflects this. There is no relationship in the population, and the relationship in my sample reflects only sampling error (occurred by chance) . 60: unlikely (low probability or p< . 05) if null hypothesis were true. Kuhn 2 (high probability of p > . 05) if null hypothesis were true. Fail to reject null hypothesis (p > . 05) Type i error made when the null hypothesis is rejected, but the null hypothesis is actually true in the population. Type ii error made when the null hypothesis is accepted, or failed to be rejected, but the alternative hypothesis is actually true in the population. If p = . 03, the null hypothesis has only 3% chance of being true. This nonsignificant difference means that there is no difference between groups.