StaTips Part VI: Bivariate correlation

  • Giuseppe Perinetti Private practice, Nocciano (PE)

Abstract


A very common situation in medical research, including orthodontics, is when a researcher has to verify the association between 2variables, best referred to as bivariate correlation. Bivariate correlation is an analysis that measures the strength of relationship between twovariables through the calculation of different correlation coefficients. The most common correlation coefficients are: Pearson (r), Kendall(rho), Spearman (rho) and the point-biserial (rpb). The choice of the correct coefficient is based on the type of data to be analysed and, forsome of them, the existence of assumptions for using parametrical tests. Indications on how to choose the correct coefficient and abouttheir interpretation are provided.

References

Glantz S. Primer of Biostatistics. 7th ed. Columbus: McGraw-Hill Education; 2011. 7th ed. ed. Columbus, OH: McGraw-Hill Education; 2011

Pearson K. Notes on regression and inheritance in the case of two parents.Proceedings of the Royal Society of London. 1895;58:240-42.

Kendall M. A New Measure of Rank Correlation. Biometrika. 1938;30:81-89.

Spearman C. The proof and measurement of association between two things. Am J Psychol. 1904;15:72-101.

Sheskin DJ. Handbook of parametric and nonparametric statistical procedure. 5th ed. ed. Boca Raton, FL: Chapman and Hall/CRC; 2011.

Perinetti G. StaTips Part I: Choosing statistical test when dealing with differences. South Eur J Orthod Dentofac Res. 2016;3:4-5.

Cohen J. A power primer. Psychol Bull. 1992;112:155-9.

Published
2019/05/13
Section
Short Communication