ABSTRACT

This chapter provides the basic concepts of hypothesis testing. The six systematic steps in testing hypotheses are: tating the null and an alternative hypothesis, selecting the level of significance, determining the test distribution, defining the critical region, performing the statistical test, and drawing the statistical conclusion. The chapter explains how the null and alternative hypotheses are formulated. It presents large and small sample tests using the mean and the proportion. The chapter explains the types of errors in hypothesis testing and provides the relationship between the a risk and the ß risk. The smallest value of a for which test results are statistically significant is called the p value. Most statistical computer programs compute the p values for different levels of significance. The use of p values reflects the desire to report the results and not to rely too heavily on arbitrarily significance levels such as.05 and.01, so that users of these results can draw their own conclusions.