Hypothesis Testing
Hypothesis testing is a formal framework for making decisions about population parameters based on sample data. You formulate null and alternative hypotheses, choose a significance level, compute a test statistic, and determine whether to reject the null hypothesis using a p-value or critical value. Understanding Type I and Type II errors is critical for interpreting results responsibly.
Solve Hypothesis Testing Problems with AI
Snap a photo of any hypothesis testing problem and get instant step-by-step solutions.
Download StatsIQKey Concepts
Study Tips
- ✓Always state both the null and alternative hypotheses in words and symbols before performing any calculations. This forces clarity about what you are testing.
- ✓Remember that failing to reject H0 does not mean H0 is true. It means you do not have sufficient evidence to conclude otherwise given your data and sample size.
- ✓Practice interpreting p-values correctly: a p-value is the probability of observing data as extreme or more extreme than what was collected, assuming H0 is true. It is not the probability that H0 is true.
- ✓Connect hypothesis testing to confidence intervals. If a 95% confidence interval for a parameter does not contain the null value, you would reject H0 at alpha = 0.05.
Common Mistakes to Avoid
The most pervasive mistake is misinterpreting the p-value as the probability that the null hypothesis is true. A p-value only tells you how surprising your data would be under H0. Students also frequently mix up Type I and Type II errors, forget to check test assumptions (normality, independence, sample size), and confuse statistical significance with practical significance. A result can be statistically significant with a tiny, meaningless effect size if the sample is large enough.
Hypothesis Testing FAQs
Common questions about hypothesis testing
A p-value of 0.03 means that if the null hypothesis were true, there would be a 3% probability of obtaining a test statistic as extreme as, or more extreme than, the one calculated from your sample. It does not mean there is a 3% chance the null hypothesis is true. If your significance level is 0.05, you would reject the null hypothesis because 0.03 < 0.05, concluding there is statistically significant evidence against H0.
A Type I error occurs when you reject a true null hypothesis (a false positive). Its probability is alpha, your significance level. A Type II error occurs when you fail to reject a false null hypothesis (a false negative). Its probability is beta. Power, which equals 1 - beta, is the probability of correctly rejecting a false null. You can reduce Type II error by increasing sample size, increasing alpha (at the cost of more Type I errors), or when the true effect size is larger.
Use a one-tailed test when you have a specific directional hypothesis before collecting data, such as 'the new drug increases recovery rate.' Use a two-tailed test when you want to detect a difference in either direction, such as 'the new drug changes recovery rate.' Two-tailed tests are more conservative and are the default in most research settings because they protect against unexpected effects in the opposite direction.