Healthcare administration leaders are asked to make  evidence-based decisions on a daily basis. Sometimes, these decisions  involve high levels of uncertainty, as you have examined previously.  Other times, there are data upon which evidence-based analysis might be  conducted.

This week, you will be asked to think of scenarios where building and  interpreting confidence intervals (CIs) would be useful for healthcare  administration leaders to conduct a two-sided hypothesis test using  fictitious data.

For example, Ralph is a healthcare administration leader who is  interested in evaluating whether the mean patient satisfaction scores  for his hospital are significantly different from 87 at the .05 level.  He gathers a sample of 100 observations and finds that the sample mean  is 83 and the standard deviation is 5. Using a t-distribution, he  generates a two-sided confidence interval (CI) of 83 +/- 1.984217  *5/sqrt(100). The 95% CI is then (82.007, 83.992). If repeated intervals  were conducted identically, 95% should contain the population mean. The  two-sided hypothesis test can be formulated and tested just with this  interval. Ho: Mu = 87, Ha: Mu<>87. Alpha = .05. If he assumes  normality and that population standard deviation is unknown, he selects  the t-distribution. After constructing a 95% CI, he notes that 87 is not  in the interval, so he can reject the null hypothesis that the mean  satisfaction rates are 87. In fact, he has an evidence-based analysis to  suggest that the mean satisfaction rates are not equal to (less than)  87.

For this Discussion, review the resources for this week, and consider  how a CI might be used to support hypothesis testing in a healthcare  scenario.

By Day 3

Post a description of a healthcare scenario where a  CI might be used, and then complete a fictitious two-sided hypothesis  test using a CI and fictitious data.