For many years, if a person experienced a heart attack and a bystander called 911, the dispatcher instructed the bystander in how to administer chest compression plus mouth-to-mouth ventilation (a combination known as CPR) until the emergency team arrived. Some researchers believe that giving instruction in chest compression alone (CC) would be a more effective approach. In the 1990s, a randomized comparative experiment was conducted in Seattle involving 518 cases (Hallstrom, Cobb, Johnson, & Copass, New England Journal of Medicine, 2000): In 278 cases, the dispatcher gave instructions in standard CPR to the bystander, and in the remaining 240 cases the dispatcher gave instructions in CC alone. A total of 64 patients survived to discharge from the hospital: 29 in the CPR group and 35 in the CC group

Research question: Is CC alone more effective than CPR in bystander situations?

Goals: In this lab, you will

• Apply the two-sample z procedures to a randomized experiment
• Consider factors that impact the strength of evidence and confidence interval in comparing two proprtions

(a) Identify the study components

(c) Suppose we want to use Fisher's Exact Test to determine the p-value.  Explain how you would set up the calculation.

Because the sample sizes are large in this study, you should not be surprised that the probability distribution in (c) is approximately normal.

The large sample sizes allow us to approximate the hypergeometric distribution with a normal distribution. Thus, with large samples sizes (e.g., at least 5 successes and at least 5 failures in each group), an alternative to Fisher’s Exact Test is the two-sample z-test that you studied in Section 3.1.

• Use the pull-down menu to select the Two Proportions option
• Enter the number of successes and sample sizes for the two groups and calculate the two-sided p-value.
• Press Calculate
• Check the Test of Significance box
• Click on the < button to convert to >

Because we are trying to use the continuous normal distribution to approximate the discrete hypergeometric distribution, we can again consider a continuity correction.  Recall that our goal is to account for the 'missing' probability at X = 35.

An advantage to using the normal approximation is being able to easily find a confidence interval for the parameter.

In the applet you can either

• Return to the original counts
• Apply the Wilson adjustment (add one additional success and one additional failure to each sample)

Return to the applet on the previous page and make your changes. Check the Confidence interval box.

Enter the observed counts into the two-way table applet, including the column and row headers.  Note you can enter a subtraction expression (e.g., 240-35) in the second row of the table and the applet will complete the calculations when you press Use Table

The evidence in this study was not particuarly strong, but combined with similar results in other studies, policy changes were made and some organizations now provide training in "hands only CPR."