Correlation Coefficients: Appropriate Use and Interpretation

Anesthesia and Analgesia - Tập 126 Số 5 - Trang 1763-1768 - 2018
Patrick Schober1,2,3, Christa Boer1,2, Lothar A. Schwarte1,2
1Published ahead of print February 23, 2018.
2the Department of Anesthesiology, VU University Medical Center, Amsterdam, the Netherlands.
3to Patrick Schober, MD, PhD, MMedStat, Department of Anesthesiology, VU University Medical Center, De Boelelaan 1117, 1081HV Amsterdam, the Netherlands. Address e-mail to [email protected].

Tóm tắt

Correlation in the broadest sense is a measure of an association between variables. In correlated data, the change in the magnitude of 1 variable is associated with a change in the magnitude of another variable, either in the same (positive correlation) or in the opposite (negative correlation) direction. Most often, the term correlation is used in the context of a linear relationship between 2 continuous variables and expressed as Pearson product-moment correlation. The Pearson correlation coefficient is typically used for jointly normally distributed data (data that follow a bivariate normal distribution). For nonnormally distributed continuous data, for ordinal data, or for data with relevant outliers, a Spearman rank correlation can be used as a measure of a monotonic association. Both correlation coefficients are scaled such that they range from –1 to +1, where 0 indicates that there is no linear or monotonic association, and the relationship gets stronger and ultimately approaches a straight line (Pearson correlation) or a constantly increasing or decreasing curve (Spearman correlation) as the coefficient approaches an absolute value of 1. Hypothesis tests and confidence intervals can be used to address the statistical significance of the results and to estimate the strength of the relationship in the population from which the data were sampled. The aim of this tutorial is to guide researchers and clinicians in the appropriate use and interpretation of correlation coefficients.

Từ khóa


Tài liệu tham khảo

Nishimura, 2016, The amount of fluid given during surgery that leaks into the interstitium correlates with infused fluid volume and varies widely between patients., Anesth Analg, 123, 925, 10.1213/ANE.0000000000001505

Kim, 2016, Morphine suppresses lung cancer cell proliferation through the interaction with opioid growth factor receptor: an in vitro and human lung tissue study., Anesth Analg, 123, 1429, 10.1213/ANE.0000000000001293

Mukaka, 2012, Statistics corner: a guide to appropriate use of correlation coefficient in medical research., Malawi Med J, 24, 69

Porter, 1999, Misuse of correlation and regression in three medical journals., J R Soc Med, 92, 123, 10.1177/014107689909200306

Schober, 2017, What do anesthesiologists know about p values, confidence intervals, and correlations: a pilot survey., Anesthesiol Res Pract, 2017, 4201289

Rodgers, 1988, Thirteen ways to look at the correlation coefficient., Am Stat, 42, 59, 10.2307/2685263

Nefzger, 1957, The needless assumption of normality in Pearson’s r., Am Psychol, 12, 623, 10.1037/h0048216

Binder, 1959, Considerations of the place of assumptions in correlational analysis., Am Psychol, 14, 504, 10.1037/h0048094

Kowalski, 1972, On the effects of non-normality on the distribution of the sample product-moment correlation coefficient., J R Stat Soc, 21, 1

Bland, 1994, Correlation, regression, and repeated data., BMJ, 308, 896, 10.1136/bmj.308.6933.896

Vetter, 2017, Fundamentals of research data and variables: the devil is in the details., Anesth Analg, 125, 1375, 10.1213/ANE.0000000000002370

Caruso, 1997, Empirical size, coverage, and power of confidence intervals for Spearman’s Rho., Educ Psychol Meas, 57, 637, 10.1177/0013164497057004009

Kwak, 2017, Statistical data preparation: management of missing values and outliers., Korean J Anesthesiol, 70, 407, 10.4097/kjae.2017.70.4.407

Bland, 1995, Calculating correlation coefficients with repeated observations: part 1–correlation within subjects., BMJ, 310, 446, 10.1136/bmj.310.6977.446

Bland, 1995, Calculating correlation coefficients with repeated observations: part 2–correlation between subjects., BMJ, 310, 633, 10.1136/bmj.310.6980.633

Overholser, 2008, Biostatistics primer: part 2., Nutr Clin Pract, 23, 76, 10.1177/011542650802300176

Bland, 2011, Correlation in restricted ranges of data., BMJ, 342, d556, 10.1136/bmj.d556

Schober, 2018;126:1068–1072, Statistical significance versus clinical importance of observed effect sizes: what do P values and confidence intervals really represent?, Anesth Analg, 10.1213/ANE.0000000000002798

Mascha, 2018, Significance, errors, power, and sample size: the blocking and tackling of statistics., Anesth Analg, 126, 691, 10.1213/ANE.0000000000002741

Ozer, 1985, Correlation and the coefficient of determination., Psychol Bull, 97, 307, 10.1037/0033-2909.97.2.307

Vetter, 2017, Magic mirror, on the wall-which is the right study design of them all? Part II., Anesth Analg, 125, 328, 10.1213/ANE.0000000000002140

Bland, 1986, Statistical methods for assessing agreement between two methods of clinical measurement., Lancet, 1, 307, 10.1016/S0140-6736(86)90837-8

Anscombe, 1973, Graphs in statistical analyses., Am Stat, 29, 17, 10.1080/00031305.1973.10478966