Select the alternative hypothesis or specify the significance level for the test.
Less than (p1 < p2): Use this one-sided test to determine whether one population proportion is less than another population proportion. This one-sided test has greater power than a two-sided test, but it cannot detect whether one population proportion is greater than another population proportion. If you select this option, the value you enter for Comparison proportions (p1) must be less than the value you enter for Baseline proportion (p2) on the Power and Sample Size for 2 Proportions dialog box.
For example, an engineer uses this one-sided test to determine whether the difference between the proportions of defective parts from two grades of material is less than 0. This one-sided test has greater power to detect whether the difference in proportions of defective parts is less than 0, but it cannot detect whether the difference is greater than 0.
Not equal (p1 ≠ p2): Use this two-sided test to determine whether two population proportions are not equal. This two-sided test can detect whether one population proportion is less than or greater than another population proportion, but it has less power than a one-sided test.
For example, a bank manager tests whether the proportion of customers who have savings accounts differs at two locations. Because any difference in the proportions is important, the manager uses this two-sided test to determine whether the proportion at one location is greater than or less than the other location.
For example, a logistics analyst uses a one-sided test to determine whether the difference in the proportions of on-time packages for two locations is greater than 0. This one-sided test has greater power to detect whether the difference in on-time deliveries is greater than 0, but it cannot detect whether the difference is less than 0.
For more information on selecting a one-sided or two-sided alternative hypothesis, go to About the null and alternative hypotheses.
Use the significance level to minimize the power value of the test when the null hypothesis (H_{0}) is true. Higher values for the significance level give the test more power, but also increase the chance of making a type I error, which is rejecting the null hypothesis when it is true.