This preview shows pages 1–2. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: Georgia Southern University, College of Business Administration BUSA 3131 Business Statistics, Assignment 11, Fall 2011 Name: _______________ When testing hypotheses, only one of the hypotheses can correctly state the outcome of the sample test. When comparing the sample mean (or proportion) values to the hypothesized value stated in the null and alternative hypothesis, the values are not exactly the same. But they are often so close numerically that researchers have difficulty deciding if the values are sufficiently different from the hypothesized value to justify rejecting the null hypothesis. To simplify the decision process, statisticians have developed simple decision rules. Numerical calculations define when a test result is sufficiently different from the hypothesized value to warrant rejecting the null hypothesis. The sample statistic must first be known and then converted to a z-value. For many situations, a sufficient collection of data over time make it possible to anticipate the population standard deviation ( ). So, if we know the standard deviation for the population and we know the expected value in the hypothesis, we can calculate the test statistics z-value with this formula:...
View Full Document
This note was uploaded on 01/30/2012 for the course BUSA 3131 taught by Professor Watson during the Fall '11 term at Georgia Southern University .
- Fall '11