Computing t Tests
The one-sample t test discussed in Chapter 6 requires that you know the population mean. It is unusual to have this information, so most studies compare two samples instead. Each sample measures a different condition of the independent variable.
Before conducting a study, it is important to know if you would need to conduct a matched-samples t test or an independent-samples t test. Independent samples consist of two groups of different people. One group has been randomly selected and is not specifically tied to who is in the other group. Matched samples are groups that are deliberately selected to be similar to each other (matched pairs) or they are the same people in both groups (repeated measures). For example, you might want to select two groups that have similar heights. If height could affect the experiment, it could be best to match the groups on that variable. This Assignment will allow you to convey your understanding of the basic concepts related to t testing and will allow you to practice setting up and conducting an inferential parametric test in SPSS.
Scenario:
Imagine you are a researcher who believes that a relaxation technique involving visualization will help people with mild insomnia fall asleep faster. You randomly select a sample of 20 participants from a population of mild insomnia patients and randomly assign 10 to receive visualization therapy. The other 10 participants receive no treatment.
You then measure how long (in minutes) it takes participants to fall asleep. Your data are below. The numbers represent the number of minutes each participant took to fall asleep.
No Treatment (X1) Treatment (X2)
22 19
18 17
27 24
20 21
23 27
26 21
27 23
22 18
24 19
22 22
Assignment:
• Explain whether you chose to use an independent-samples t test or a matched-samples t test. Provide a rationale for your choice.
• Identify the independent and dependent variables.
• Knowing you believe the treatment will reduce the amount of time to fall asleep, state the null and alternate hypotheses in words (not formulas).
• Explain whether you would use a one-tailed or two-tailed test and why.
• Explain whether you have homogeneity of variance, and explain how you know. Explain why it is important to know if you have homogeneity of variance.
• Identify the obtained t value for this data set using SPSS.
• Identify the degrees of freedom and explain how you determined it.
• Identify the p value.
• Explain whether you should retain or reject the null hypothesis and why.
• Explain what you can conclude about the effectiveness of visualization therapy.