Hypothesis Testing

Overview

Often in research and data analysis, we want to investigate certain new claims that challenge what is currently believed, so we take some sample data and see whether or not it supports our new claim. Hypothesis testing is a reliable way to take sample data and test how strongly its evidence supports our new claim – if the evidence is strong, we can reject the old beliefs and support the new; if it is weak, we cannot reject the old beliefs.

Learning Goals

1. Identify appropriate null and alternative hypotheses for a problem scenario, and effectively interpret test conclusions in terms of the hypotheses/practical scenario.

2. Calculate and interpret test statistic, p-value, and alpha level, and understand how to use them to make a conclusion.

3. Define and interpret Type I and Type II errors, and calculate their probabilities, given various parameters such as alpha, sample size, and testing power. Understand the conditions/assumptions under which each type of error may occur.

This app was developed by Abbey List in Summer 2020.