The goal of the project is to introduce the process researchers use to design an observational study. Researchers at reputable institutions are required to create a detailed proposal before embarking on an experiment or observational study to an Institutional Review Board (IRB). An IRB is a type of committee that applies research ethics by reviewing the methods proposed for research to ensure that they are ethical. Such boards are formally designated to approve (or reject), monitor, and review biomedical and behavioral research involving humans. They often conduct some form of risk-benefit analysis in an attempt to determine whether or not research should be conducted. The purpose of the IRB is to assure that appropriate steps are taken to protect the rights and welfare of humans participating as subjects in a research study.
Ultimately, the IRB needs the researcher to show that the experiment or study is useful (it will contribute to the scientific understanding of some process) and relatively safe.
Step 1:
Articulate a hypothesis to test. Pick something that is interesting to you in an area that you know a lot about. Your study must have human subjects. The hypothesis needs to conform to one of the following methods:
1. Two-sample test for mean.
2. Two-sample test for proportion.
3. Chi-squared goodness of fit test.
4. Chi-squared test of independence.
Don't describe the test with mathematical notation yet. Describe it in several sentences. Explain why your test is interesting and important to you. Outline any ethical considerations and how you would deal with them. Would you need to obtain "informed consent"?
Don't worry about whether you can carry out the test. For instance, suppose you want to poll people at your work, don't worry about whether your manager would let you.
Step 2:
Specifically identify your populations.
Step 3:
Explain your sampling procedure. Make sure to address the following.
1. How will you make sure that the sample is representative?
2. How will you make sure the sample isn't biased?
3. How will you make sure you are sampling the correct people?
4. What sampling method will you use (cluster, stratified, etc.)?
Step 4:
Explain what data you will collect and how.
1. What size will your sample need to be?
2. How would you generate a random sample?
3. What will you do with your sample? Will you ask them questions? If so, what questions? Will you measure the subjects? If so, what measurements?
Step 5:
What method will you use to analyze your study?
1. State in mathematical notation your exact hypothesis.
2. Why is the method you choose appropriate to use?
Step 6:
What new knowledge will your study contribute to society? How is it important?