What is a hypothesis test?
Learning outcomes:
On watching this video, students should be able to:
- Explain why we use a hypothesis test and differentiate it from the information contained in a confidence interval.
- Write down the null hypothesis given a research question or study outline.
- List the three main steps of a hypothesis test.
- Explain what a test statistic is and how it is used it to calculate a p-value.
- Explain the term significance, and how a hypothesis test is often used to make a decision about whether to reject or fail to reject the null hypothesis.
- Explain why we either reject or fail to reject the null hypothesis and do not say that we have proved the null hypothesis.
- Interpret a p-value as a continuous measure of the strength of evidence against the null hypothesis, and explain why the dichotomous interpretation of p-values as significant or not significant is arbitrary and generally should be avoided.
- Explain the difference between a one-sided (one tailed) and two sided (two-tailed) hypothesis test and why a two-tailed test is the default.
- Describe the difference between statistical and practical (clinical) significance and link this why it is often useful to report both a p-value and a confidence interval when reporting results.