Fundamentals of Quantitative Research
David E. McNabb · 2017
Null hypotheses are always stated in terms of either the status quo or as no difference. This chapter examines a representative few of the statistical tools used to test for significant differences between parametric statistics for two or more groups or subgroups. The underlying concepts of hypothesis testing in apply to a body of statistical techniques designed to test hypotheses about two or more samples. These tools permit managers to test whether the different values found in two or more samples are statistically significant or whether they could have occurred by chance. Difference tests also weigh disparities between two or more groups in their rankings or ratings of a set of items, resulting in ordinal- and interval-level data, respectively. The small-sample t-test and large-sample F-test, probably the most commonly encountered difference tests, look for differences between the mean scores of two or more groups. These two tests should only be used with interval or ratio data.