 Step-By-Step Guide
Resources
Step-By-Step Guide
Task 2.6: Design a Case-Control Study
You and your colleagues have been asked to design a case-control study and to update the questionnaire so the wording is appropriate for controls (non-patients).
The steps below will walk you through this process.
- Review the email from Dr. Lyons to confirm your understanding of the task.
- Download and review the Case-Control Study Template, which is attached to Dr. Lyons’ email.
- Each team member should download a copy and keep his/her own notes. Each of you may notice different things, which will be helpful to share with each other and discuss.
Design the Case-Control Study
There are many components to designing the case-control study, but you will be responsible for three of them: defining the hypothesis or hypotheses that the case-control study will be investigating, defining the power or size of the study, and defining the controls. For each component keep in mind the following:
- Consider the time and resources that you have available to you on this project.
- Consider the balance between the importance of minimizing costs and maximizing what you will be able to investigate based on the data you get back from the study.
- Begin by evaluating the hypotheses that remain after your last analysis. Discuss with your teammates the following questions in order to reduce the number of possible hypotheses with which to enter the case-control study. Document your final hypotheses separately (with justification) in the Case-Control Study Template.
- Which possibilities remain given all that you have learned to this point about the source of the outbreak?
- After further discussion, are there any hypotheses that you can eliminate based on what you know?
- Once you have narrowed down your hypotheses, you are ready to define your controls.
- Use what you know about case-control studies, the information you’ve gathered in the Line Listing v2, the statistics you developed in the Descriptive Epi Report, and what information is available to you in the Resources (above) to make these determinations.
- Document each matching criteria separately with justification for each in the Case-Control Study Template.
- Note: the criteria listed in the template are criteria frequently used to match controls to cases. You may or may not need to use every criteria listed. Document "Do not use" for any criteria you decide not to use, and the justification for doing so.
- Describe the method you suggest using to achieve matching on the criteria. For some criteria the only way to find the data is to ask potential controls whether they meet the criteria or not (see point 2 in Revise the Questionnaire (below)). There may be other ways to accomplish matching on other criteria that will save time and money.
- Determine the size of the study. You’ll find information on sizing a study in the Resources, (above). After you read through the supporting materials, you will need to make a decision about whether you need to have 1, 2, 3 or 4 times as many controls as cases. Document your decision along with its justification in the Case-Control Study Template.
- Make sure to include enough controls so the study has enough power to detect differences. Not including enough controls may lead to a Type II error, a false negative, and mislead the investigation team. Including too many controls will unnecessarily consume time and resources.
Revise the Questionnaire
The questionnaire used to gather information from the case-patients has questions phrased in a way that assumes the people being surveyed have been ill (if they weren’t ill they wouldn’t be cases). In order to be used in the case-control study the wording in the questionnaire needs to be modified.
- Retain all the questions from the original questionnaire. In order to make accurate comparisons between case-patients and controls you need to have the same data.
- Although the Revised Questionnaire will likely run over the general rule of 10-15 minutes and controls have less vested interest than cases, the people administering the questionnaires are professionals and will be able to keep the respondents engaged for the extended period of time needed to answer all questions.
- Add a question or questions to the beginning of the questionnaire, right after the introduction, for any criteria you have chosen to use for control selection. For example if you have controlled for age, add a question in the beginning about the age of the respondent to identify whether they fit the qualifications needed for the study.
- Since the questions were originally written for the case-patient audience and assumed the respondent to be sick, the questions now need to be revised for a well population. Go through each question on the questionnaire and revise the wording as needed so that it is appropriate for controls. Make sure that the new wording doesn’t change the meaning of the question.
- Remember that by definition, a control cannot have the illness under investigation.
- Make sure to remove ALL references to "patient," "symptoms," and cocci "illness.
- Use "in the last 3 months" instead of "in the 6 weeks prior to symptom onset."
Reflection Questions
Look at the reflections questions in Reflect on what you learned" (above). Answer each question as described in the instructions there.
Review and Submit your Work
- Review your work.
- Did you discuss all aspects of your hypotheses, including all members of the team and retaining only the most durable possibilities?
- Did you select your matching criteria carefully, being mindful of the risks of overmatching?
- Did you consider all the elements in determining the size of your study?
- Did you revise the questionnaire to fit the case-control study without changing the data that will be gathered from each question?
- Submit your work.
- Review the checklist located in the Submit Your Work section of this task to ensure completion of the task before submitting your deliverables to your mentor.
- Please note: Only one set of deliverables need to be submitted per team. Any additional notes not captured in that set of deliverables should be retained by the team members for possible use in future tasks.
Resources
Task 2.6 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.
Ask the Expert
 What is the benefit of matching in a case-control study?
What are the disadvantages to matching in a case-control study?
General Resources
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.
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.
Matching Controls for a Case-Control Study
Information on different ways to select controls and problems that can arise from the improper selection of controls.
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.
Risk Factors for Sporadic Giardiasis
A Case-control study of sporadic giardiasis. Pay attention to the number of controls in this study relative to the number of cases in the study. This is a technical paper intended for advanced audiences so don’t get too frustrated if some of the information presented is difficult to understand.
Sampling Methods
A resource from Wikipedia on different types of sampling methods.
|
