Define and differentiate Type I and Type II error.

Question

What will be an ideal response?

Answer 1

Ans: Varies.

Type I error occurs when researchers falsely reject a null hypothesis. Researchers find a statistically significant result but in actuality the null is true. Because statistical testing is based on probability, we expect that researchers will make this type of error at the rate of their cutoff for significance (e.g., 5%). Chance alone tells us that it is possible to obtain results in the tails of the null distribution even if the null distribution is actually true. Type II error occurs when we fail to reject a null hypothesis that is false. Here, researchers’ results fall into the “acceptance” region of the null distribution even though in actuality, population means are not the same. The probability of committing a Type II error decreases with larger sample sizes, decreases with larger effect sizes, and is directly tied to the level of significance.