Module 8 – Treating Depression Lab Part 2 (discussion 2) – mod 8 group 4

Learn by Doing

In this activity, you will investigate the first question related to the study described below.

Some features of this activity may not work well on a cell phone or tablet. We highly recommend that you complete this activity on a computer.

Here are the directions and grading rubric for the Learn by Doing discussion board exercises.

A list of StatCrunch directions is provided at the bottom of this page.

Context

Clinical depression is a recurrent illness requiring treatment and often hospitalization. Nearly 50% of people who have an episode of major depression will have a recurrence within 2-3 years. Being able to prevent the recurrence of depression in people who are at risk for the disease would go a long way to alleviate the pain and suffering of patients.

During the 1980’s the federal government, through the National Institutes of Health (NIH), sponsored a large clinical trial to evaluate two drugs for depression. There were 3 treatment groups. Patients received either Imipramine (Imip), Lithium (Li), or a Placebo (Pl). Researchers randomly assigned patients to one of the 3 treatment groups and followed them for 2-4 years to track any recurrences of depression.
(Prien et al., Archives of General Psychiatry, 1984).

Variables

• Hospt: Which hospital the patient was from: Labeled 1, 2, 3, 5 or 6
• Treat: 0=Lithium; 1=Imipramine; 2=Placebo
• Outcome: 0=Success 1=Failure (recurrence of depression)
• Time: Number of weeks until a recurrence (if outcome=1) or until study ended (if outcome=0)
• AcuteT: How long the patient was depressed before the start of the current study, measured in days
• Age: Age in years
• Gender: 1=Female 2=Male

Data

If you have not done so already, download the depression datafile (as always, if a login box opens, just close it and then download the file). Then upload the file in StatCrunch.

Prompt

We will analyze the data to answer the second research question: Which of the drugs (if either) delayed the recurrence of depression longer relative to the placebo?

In the previous lab-preparation activity, we identified Treat as the explanatory variable and Time as the response variable. We also determined that we will analyze the data using side-by-side boxplots and descriptive statistics (i.e. 5-number summaries since the graphs are boxplots).

1. Make graphs and tables.
   1. Use StatCrunch to produce side-by-side boxplots. (directions)
      Embed your graphs with your initial post.
   2. Use StatCrunch to produce the descriptive statistics (a table containing the 5-number summaries for each comparison group). (directions)
      Copy and paste the StatCrunch output table into your initial post.
2. Analyze the data: Compare the distributions for the treatment groups as demonstrated in Unit 2. For example, compare medians and intervals of typical values. Describe the shape and any outliers. Be sure to write your comparisons so the reader can understand the context of the numbers. For example, don’t just say the median is 30; instead, say something like this: on average patients taking the placebo relapsed in 30 days (Q2=30 days).
3. Draw a conclusion: What can we conclude from your analysis? Did one drug successfully delay a relapse of depression better than the others? What evidence supports your conclusion?
4. Summarize your conclusions in response to both research questions: In this lab you compared three treatments using two different variables: (Parts 1 & 2) whether or not a relapse into depression occurred and (Parts 3 & 4) if a relapse occurred, the time it took to occur. What can you conclude in light of both analyses? Is one treatment better than the other? How does the data support your conclusion?

List of StatCrunch Directions

Each link will open in a new window. To return to this discussion, either close the new tab or select the tab for this discussion.

• Create Your Stats-Class Folder in Canvas (You only need to do this once.)
• Purchase StatCrunch (You only need to do this once.)
• Open StatCrunch
• Download Excel Data File
• Upload Excel Data File to StatCrunch
• Download StatCrunch Output Window (no screenshots; please use these directions)
• Upload Files into Your Stat-Class Folder in Canvas
• Embed Pictures in a Discussion Post (no attachments; please use these directions)
• Copy & Paste a StatCrunch Table
• Side-by-side boxplot
• Descriptive Statistics Across Multiple Categories

Here is a PDF document with all StatCrunch directions (Links to an external site.).