Category: Exclusions in research studies. These pages discuss the problems with generalizability that occur when researchers include important segments of the population from their research or when research subjects refuse to participate. Articles are arranged by date with the most recent entries at the top. You can find the theme and closely related categories and other resources at the bottom of this page.

Stats: Characterizing reasons for refusal (January 17, 2006). A participant in the IRB Forum raised a question about a research study where people were asked to participate, and when some of them said "no" they were then asked why they did not want to participate. The  reasons were tallied across all of the refusals, and percentages were published as part of the full research study. Since the people had already said "no" to participating in the research study, did that also imply that they did not want to share information about their reasons for not participating?

Stats: Excluding placebo responders (June 25, 2004). I've always been fascinated by the placebo effect and the ethical issues associated with use of placebos in research. A correspondent in the IRBForum email discussion group asked about the recent efforts of drug companies to identify patients who are likely to show a placebo effect and then exclude them from randomized trials.

Stats: Selection bias (August 24, 2004). The CarTalk radio show has an interesting puzzle every week and often these puzzles involve mathematics. These puzzles can sometimes help you understand complex mathematical concepts that are important in Statistics. In the summer, they re-use puzzlers from earlier years, and just last week, they re-used one of my favorites. A "nameless mathematician" during World War II was asked to help with a military problem. A lot of bombers were not returning from their missions, so the Royal Air Force wanted to put armor on the bombers. But where to put it?

Stats: So you want to volunteer for a research study? (August 4, 2004). Here's a draft of a speech that I am planning to give on August 5, 2004 for the Bluejacket Toastmasters humorous speech competition. So you want to volunteer for a research study? Good for you! Mister Contestmaster, fellow Toastmasters, and Guests. I work as a statistician at Children's Mercy Hospital. So when you volunteer for a research study, you provide the data that gives me job security.

Theme and closely related categories:

• Theme: Evidence based medicine
• Category: Extrapolations in research

Other resources:

• Are subjects in pharmacological treatment trials of depression representative of patients in routine clincal practice? Description: This article compares the typical patients with depression treated in routine clinical practice against the exclusion criteria used in a standard clinical trial of depression. Ony 41 of the original 346 patients would have been eligible for enrollment in a typical clinical trial.
• Major Deficiencies in the Design and funding of Clinical Trials:  A Report to the Nation Improving on How Human Studies are Conducted [PDF] Excerpt: Clinical trials are a critical resource for the discovery of new, life-saving drugs and for developing better prevention and diagnostic screening methods. Today’s most effective prevention and treatment modalities are based on previous clinical trial results. But while the need for clinical research is undisputed, how clinical trials are now conducted remains problematic. Increasing research finds major deficiencies in the way clinical trials are designed, carried out and funded in the U.S. with serious implications for the outcomes of medical research studies. Of key significance for the future of scientific innovation is the exclusion or underrepresentation of women, older people, minorities, disabled persons, and rural populations in the vast majority of the research studies conducted in the U.S. Without adequate representation of all patient populations, researchers cannot learn about potential differences among groups and cannot ensure the generalization of results.

Not yet in proper format

1. Randomization Process in Question: Efficacy Trials Evaluating Psychotherapy vs Medications May Not Be Valid
2. Record linkage research and informed consent: who consents?

[Return to full topic list] [Read current weblog entries]

This webpage was written by Steve Simon on 2007-06-18, edited by Steve Simon, and was last modified on 2008-10-13. Send feedback to ssimon at cmh dot edu or click on the email link at the top of the page.