Social Statistics for a Diverse Society
Chapter Summary
Chapter 9
Statistical hypothesis testing is a decision-making process that enables us to determine whether a particular sample result falls within a range that can occur by an acceptable level of chance.The process of statistical hypothesis testing consists of five steps: (1) making assumptions, (2) stating the research and null hypotheses and selecting alpha, (3) selecting a sampling distribution and a test statistic, (4) computing the test statistic, and (5) making a decision and interpreting the results.
Statistical hypothesis testing may involve a comparison between a sample mean and a population mean or a comparison between two sample means.If we know the population variance(s) when testing for differences between means, we can use the Z statistic and the normal distribution.However, in practice, we are unlikely to have this information.
When testing for differences between means when the population variance(s) are unknown, we use the t statistic and the t distribution.
Tests involving differences between proportions follow the same procedure as tests for differences between means when population variances are known.The test statistic is Z, and the sampling distribution is approximated by the normal distribution.