Cohorte 2) Groupe de référence

Cohorte 2) Groupe de référence

by Thierry Ancelle

Applied Sciences & Engineering Medicine & Health MBNPublic health and preventive medicineMBNSEpidemiology and Medical statistics
🎙 Thierry Ancelle 👥 25K 📅 December 31, 2022 ⏱ 13 min 👁 9K 📄 tutorial 🧭 2026-08-17
Available in: English (current) Français

Keywords

cohortreference groupsample sizerisk ratioselection bias

Summary

This video is the second part of a course on cohort studies, focusing on the selection of a reference (non-exposed) group and the estimation of required sample size. The instructor explains why a reference group is necessary to compare disease incidence and calculate relative risk. He outlines three key rules for selecting a reference group: subjects must come from the same population, have the same potential for follow-up, and have the same baseline risk of disease. He illustrates these rules with a real example of a vaccine efficacy study in Alaska, where an initial flawed comparison led to a paradoxical result, corrected by choosing a comparable reference group. The video then discusses strategies for selecting reference groups, such as using the entire source population in closed cohorts or internal comparison groups with varying exposure levels. Finally, he presents the formula for calculating sample size, explaining the parameters involved (alpha, beta, incidence rates, minimum detectable relative risk) and demonstrates how changing these parameters affects the required sample size. He emphasizes the importance of this calculation in protocol design and suggests using software for these computations.

184 words

Critical Evaluation

Value of the Information & Strength of the Argument

The video provides valuable practical guidance for designing cohort studies, particularly for selecting appropriate reference groups and calculating sample size. The argumentation is solid, using a clear real-world example to illustrate the consequences of selection bias. The instructor logically builds from the need for a reference group to the rules for its selection, and then to the quantitative aspect of sample size. The explanation of the sample size formula is accessible, breaking down each component and its role. The use of an example with changing parameters effectively demonstrates the trade-offs between power, significance level, and effect size. The video is well-structured and the reasoning is coherent, making it a useful educational resource.

Scientific Rigor, Source Quality, Title Accuracy

The scientific rigor is adequate for an educational tutorial. The instructor references standard epidemiological concepts and provides a real example, but does not cite specific studies or sources in detail. The description includes links to his own course materials and to an online calculator (epitools), which are relevant. The title accurately reflects the content. The video does not include any advertising or sponsored content.

191 words

Title / Content Match

The title accurately reflects the content, which focuses on the reference group in cohort studies.

Quality & Reliability

8/10

The video is a clear and structured tutorial on selecting reference groups and calculating sample size for cohort studies. It uses a real example (vaccine efficacy in Alaska) to illustrate selection bias, and provides practical formulas and software recommendations. The content is consistent with standard epidemiological methodology, though it lacks detailed citations to primary literature.

Key Moments

Markers derived by PSI from the transcript: the creator did not define chapters.

Cited Sources

Concurring Sources

External References

Contribution & Novelties

The video provides a clear and practical guide to selecting reference groups and calculating sample size for cohort studies, emphasizing common pitfalls such as selection bias. It offers a step-by-step approach to sample size calculation, making it accessible to students and researchers.

Pour aller plus loin :

80 words

Radar Profile

The radar profile shows high scores in information quantity, quality, and technical level, with a slightly lower but still good score in global reliability. This indicates a well-structured and informative tutorial with minor limitations in sourcing.

Reliability 8/10

💬 No comments were provided for analysis.