Introduction to Hypothesis Testing for One Population Mean
Recall that we reject the null hypothesis and conclude that we have statistical significance if our p-value is less than the significance level \(\alpha\). Now we extend these ideas into hypothesis testing about means, first focusing on a single population mean.
Note the following three notes of caution:
- Your sample must be representative of the population.
- One way to get representative sample is a random sample
- Hypotheses/conclusions apply to larger populations represented by the samples.
- If the distribution is highly skewed, consider analyzing by the median rather than the mean – nonparametric methods.
Basic Steps
- Determine \(H_0\) and \(H_A\)
- Verify necessary data conditions.
- For proportions, the standardized statistic is called a z statistic which has the \(N(0,1)\) distribution.
- For means, the standardized statistic is called a t statistic which has a t distribution.
- Find the p-value.
- Decide if the result is statistically significant based on the p-value.
- Report conclusion in the context of the situation.