Coefficient de corrélation de Spearman

Coefficient de corrélation de Spearman

by Thierry Ancelle

Formal & Physical Sciences Mathematics PBMathematicsPBTProbability and statistics
🎙 Thierry Ancelle 👥 25K 📅 March 28, 2015 ⏱ 13 min 👁 42K 📄 tutorial 🧭 2026-08-17
Available in: English (current) Français

Keywords

Spearmanrank correlationnon-parametric teststatistical testtutorial

Summary

This educational video by Thierry Ancelle, part of a series on statistics and epidemiology, explains the Spearman rank correlation coefficient. It begins by contrasting it with Pearson’s correlation, emphasizing its use when data do not meet normality assumptions. The presenter demonstrates how to compute Spearman’s rho using ranks, including handling ties (ex aequo) with Excel’s RANK function and the alternative of averaging ranks as done in software like Stata. The interpretation of the coefficient (ranging from -1 to +1) is explained, and the hypothesis test for significance is detailed, using a t-distribution with n-2 degrees of freedom. A worked example with 30 serum samples shows a strong positive correlation (rho=0.81) that is highly significant (p<10^-6). The video also covers conditions of application (random variables, independent observations, n>10, few ties) and highlights the advantage of Spearman over Pearson when normality is violated. A cautionary example illustrates how Pearson’s correlation can be misleading with outliers, while Spearman is robust. The presenter concludes by reminding that correlation does not imply causation, and recommends textbooks and an online tool (BiostatTGV) for further practice.

179 words

Critical Evaluation

Value of the Information & Strength of the Argument

The video provides a solid introduction to the Spearman correlation, with clear explanations and practical examples. It effectively demonstrates the calculation process, including the handling of ties, and the use of statistical software. The argumentation is logical and well-structured, building on previous knowledge of Pearson correlation. The presenter emphasizes the advantages of Spearman in non-normal data and its robustness to outliers, which is a key point. However, the video does not delve into the mathematical derivation of the formula or the test statistic, which might be a limitation for advanced learners. Overall, the content is valuable for students and practitioners needing a practical understanding of this non-parametric method.

Scientific Rigor, Source Quality, Title Accuracy

The video is scientifically rigorous, presenting standard statistical methodology for the Spearman correlation. The presenter is an expert in biostatistics, and the content aligns with established textbooks. However, no specific academic sources are cited within the video, and the recommended resources (Schwartz and Bouillet textbooks, BiostatTGV website) are mentioned but not detailed. The title accurately reflects the content. The video is a tutorial, so it does not provide original research, but it is a reliable educational resource.

200 words

Title / Content Match

The title accurately reflects the content, which focuses exclusively on the Spearman correlation coefficient.

Quality & Reliability

8/10

The video provides a clear, step-by-step explanation of the Spearman rank correlation coefficient, including calculation, hypothesis testing, and interpretation. The presenter is an expert in biostatistics, and the content aligns with standard statistical methodology. However, the video is a tutorial and does not cite specific peer-reviewed sources, and the presentation is somewhat dated (2015).

Key Moments

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

Cited Sources

Concurring Sources

Contribution & Novelties

This video provides a clear and practical tutorial on the Spearman rank correlation coefficient, emphasizing its application in medical and biological statistics. It effectively demonstrates the calculation process, including the handling of ties, and the use of statistical software. The video also highlights the advantages of Spearman over Pearson in non-normal data and its robustness to outliers, which is a key point. It serves as a valuable educational resource for students and practitioners.

Pour aller plus loin :

123 words

Radar Profile

The radar chart shows a balanced profile with high scores in information quantity, quality, and reliability, and a slightly lower score in technical level, indicating that the video is accessible yet informative, suitable for learners with basic statistical knowledge.

Reliability 8/10

💬 No comments were provided for analysis.