Stats Task 3.1: Case Control Studies and Interpreting Odds Ratios

You have been asked to respond to Andy, who has questions about why his team chose the case-control study for their investigation at the Tip Hotel. In addition, he needs help in determining what the odds ratios tell him about the likely cause of the outbreak at the food banquet.

The following step-by-step guide will help you do your work.

1. Before you begin your work, find a peer to work with for this task. Although each of you will be responsible for submitting your own work, you may work with one another to better analyze the question and come up with the important components of your response. You may partner with someone you have worked with before, with more than one person, or as otherwise advised by your mentor.
   
   
2. Review the email and make sure you understand what questions you are being asked to answer in this task. It may be helpful to print a copy of the email as it also contains the results of the investigation which you will need to answer questions about what the results mean.
   
   
3. Review the Resources available for this task, specifically the FAQs, which will help you to consider the important characteristics and differences between the case-Control and cohort studies. You will refer back to these FAQs throughout this task.

Compare and Contrast a Case-Control and Cohort Study

Each study is designed for different purposes and gives the researcher different results. Determining which study to conduct is an important step in epidemiology and this mini-task will give you some experience with the different studies so you can better answer Andy’s questions.

Tip: If you have any difficulty during this mini-task, go back to the Resources section first. If you still have questions, check-in with your mentor.

1. In the Resources section (above), review the Case-Control and Cohort Study FAQ. The FAQ provides an overview of the two types of studies and describes what the calculations in each study mean. It may be helpful to refer back to this file periodically as you complete the other parts of this task which give more concrete examples.
   
   
2. In the Resources section, review the Synopsis of Doll and Hill’s Studies about two important studies about smoking and lung cancer. As you are reviewing the Synopsis, discuss the following questions within your team:
   1. In Doll’s case-control study:
      
      
      • What does Doll start with? Does he start by looking at the exposure (smoking) or the outcome (lung cancer)?
        
      • What does he seek to find out? When answering this question, consider the study design and whether or not the results of the study can answer the research question.
        
      • How did he define the two comparison groups in this study? Who are the cases? Who are the controls?
        
      • Why do you think Doll chose a case-control study instead of a cohort study?
        
      • What do the odds ratios tell you about the relationship between smoking and lung cancer?
        
2. In Hill’s cohort study:
   
   
   • What does he start with? Does he start by looking at the exposure (smoking) or the outcome (lung cancer)?
     
   • What does he seek to find out?
     
   • How did he define the cohort?
     
   • Why do you think Hill chose a cohort study rather than a case-control study?
     
   • What does the risk ratios (relative risks) tell you about the relationship between smoking and lung cancer?
     
     
3. What does the cohort study tell you that the case-control study cannot tell you?
   
   
4. Given the answer to the above question, why might Doll have used a case-control study rather than a cohort study?

Tip: Analyzing the questions in this task in depth rather than superficially will help make the abstract principles listed in the FAQ more tangible, making it easier to distinguish between the two types of studies more accurately.

Review the Banquet Example

Now think about the banquet investigation that Andy summarizes in his email. Please Note: the banquet study is different from Doll’s case-control study because it looks at many different exposures, not just one (e.g., smoking). In other words, Andy’s team is evaluating multiple food items for possible contamination.

1. With your partner, answer the following questions:
   
   1. In this study, what did the team know at first? Did they know there was an outcome (outbreak or illness) or an exposure?
      
      
   2. In their investigation, what are they trying to find out?
      
      Tip: Think in terms of exposures and outcomes.
      
      
   3. Why didn’t the team choose to do a cohort study at the Tip hotel banquet?
      
      
   4. How would the two comparison groups be defined in this study? Who are the cases? Who are the controls?
      
      
   5. What does the OR tell you about the relationship between each food and getting sick? Beef? Gravy? Potatoes? Vegetables? Fish? Chicken? Lasagna? Pasta Salad? Chocolate Cake? Carrot Cake? Etc.
      
      
   6. Which food(s) are associated with getting sick?
      
      
   7. Why might the results show that the people who became ill had greater odds for eating multiple foods and not just one food? Other than the possibility that multiple foods were contaminated, what other explanation(s) could there be for more than one food showing an association?
      
      

Drafting the Email Response

1. This time without your peer, draft an email response answering Andy’s questions about his team’s study.
   
   
   • Tell Andy why you think his team chose the case-control over the cohort for their investigation at the Tip hotel. Make sure to identify which factors are important to consider when deciding between doing a Case-Control or a Cohort study so that he will be able to answer similar questions that may arise in the future without assistance.
     
     
   • Tell Andy what the results of the banquet case-control study tell him about which food(s) are likely to be contaminated. Make sure to tell him how you determined which food(s) were of concern, and generally how to interpret Odds Ratios.
     
     
   • Make your email response clear and concise.
     
     
2. Next, conduct a review of your email responses by exchanging responses with your peer.
   
   
   • Review one another’s email response to determine if the email meets the requirements listed above. If an email response does not meet all of the requirements, help one another identify how it can be modified to be more clear and/or complete.
     
     
   • While it is appropriate to work together on this task, make each of your responses unique, including unique examples as appropriate, to reflect your own work and thinking.
     
     
3. Submit your individual response to your mentor. Review the checklist located in the Submit Your Work section of this task before submitting your response to your mentor.

Stats Task 3.1 Resources

The resources below will help you get started on this task. You may decide to do additional research to help clarify concepts, or to gain a deeper understanding of the subject matter. View the General Skills Resources link on the left for more information on research including evaluating web resources.

While Wikipedia is a valuable resource, unlike some other websites anyone can contribute to or modify the site (whether they're knowledgeable about the topic or not). As a result, the site is subject to constant change by questionable sources. Be sure to cross-check information on Wikipedia with other reputable sites to ensure accuracy.

Hypotheses and the Scientific Method FAQ
This FAQ supports you in creating and testing scientific hypotheses, with examples and explanations.

Hypotheses for Epidemiology FAQ
General information on hypotheses and testing with emphasis on hypotheses for epidemiology studies.

Synopsis of Doll and Hill’s Studies
A description of Doll and Hill's classic case-control and cohort study on the relationship between smoking and lung cancer. Includes a comparison of the two types of studies.

Case-Control and Cohort Study FAQ
Frequently Asked Questions about Case-Control and Cohort studies including the steps involved in each study, the advantages and disadvantages to each, how to calculate Odd Ratios and Relative Risk, and how to interpret the results.

Case-Control Studies and Refining Hypotheses
Information on case-control studies, selecting controls, and refining hypotheses. The first two pages and the last two pages are the most informative for this task.

Case-Control and Cohort Diagram
A visual diagram of the two types of studies, including participant selection and the relation of exposures and outcomes in each group.

Ask the Expert

What factors would lead you to choose a case-control study?

What factors would lead you to choose a cohort study?

What are the measures of association?