Investigators want to explore a possible association between the use of nonsteroidal antiinflammatory drugs (NSAIDs) and the development of Crohn disease. They plan to administer a standardized questionnaire on NSAID use over the past year to patients with newly diagnosed Crohn disease and to age- and sex-matched healthy volunteers. The study design is most concerning for which of the following?
A)Lack of external validity
B)Lack of statistical power
C)Length time bias
D)Misclassification of exposure
E)Misclassification of outcome

Question

Investigators want to explore a possible association between the use of nonsteroidal antiinflammatory drugs (NSAIDs) and the development of Crohn disease.  They plan to administer a standardized questionnaire on NSAID use over the past year to patients with newly diagnosed Crohn disease and to age- and sex-matched healthy volunteers.  The study design is most concerning for which of the following?
A)Lack of external validity
B)Lack of statistical power
C)Length time bias
D)Misclassification of exposure
E)Misclassification of outcome

Quizplus · Accepted Answer

Explanation: Recall bias results from the inaccurate recall of past exposure by participants in a study. It applies mostly to case-control designs and leads to misclassification of exposure. Individuals with a disease are more likely to search their memories to try to identify whether an exposure has contributed to their condition. This study is assessing a potential association between nonsteroidal antiinflammatory drug (NSAID) use and Crohn disease. Patients with newly diagnosed Crohn disease may be more likely to recall NSAID use over the past year as they complete the questionnaire. (Choice A) External validity (or generalizability) is defined as the applicability of a study's results beyond the group that was initially assessed. It answers the question, "How generalizable are the results of a study to other populations?" External validity is not a concern as this study's results may be applicable to other individuals with Crohn disease. (Choice B) There is no information regarding sample size, which would help determine statistical power. However, recall bias would still be the primary concern even with an adequate sample size. (Choice C) Subjects with a rapidly progressive form of disease are less likely to be detected by screening compared to those with slowly progressive disease. This length time bias tends to overstate the beneficial effects of screening on length of survival and mortality. However, this study is less concerned with screening as the diagnosis of Crohn disease has already been made. (Choice E) The outcome (Crohn disease development) is known in this example, so misclassification of outcome is unlikely. Educational objective: Recall bias results from the inaccurate recall of past exposure by participants in a study. It applies mostly to case-control designs and leads to misclassification of exposure. References: Bias and causal associations in observational research. (http://www.ncbi.nlm.nih.gov/pubmed/11812579)

Investigators Want to Explore a Possible Association Between the Use