Correlation and dependence
is any statistical relationship, whether causal
or not, between two random variables
or bivariate data
. In the broadest sense correlation
is any statistical association, though it commonly refers to the degree to which a pair of variables are linearly
related. Familiar examples of dependent phenomena include the correlation between the height
of parents and their offspring, and the correlation between the price of a good and the quantity the consumers are willing to purchase, as it is depicted in the so-called demand curve
Several sets of (x
) points, with the Pearson correlation coefficient
for each set. The correlation reflects the noisiness and direction of a linear relationship (top row), but not the slope of that relationship (middle), nor many aspects of nonlinear relationships (bottom). N.B.: the figure in the center has a slope of 0 but in that case the correlation coefficient is undefined because the variance of Y
Correlations are useful because they can indicate a predictive relationship that can be exploited in practice. For example, an electrical utility may produce less power on a mild day based on the correlation between electricity demand and weather. In this example, there is a causal relationship
, because extreme weather causes people to use more electricity for heating or cooling. However, in general, the presence of a correlation is not sufficient to infer the presence of a causal relationship (i.e., correlation does not imply causation
Formally, random variables are dependent
if they do not satisfy a mathematical property of probabilistic independence
. In informal parlance, correlation
is synonymous with dependence
. However, when used in a technical sense, correlation refers to any of several specific types of mathematical operations between the tested variables and their respective expected values
. Essentially, correlation is the measure of how two or more variables are related to one another. There are several correlation coefficients
, often denoted or , measuring the degree of correlation. The most common of these is the Pearson correlation coefficient
, which is sensitive only to a linear relationship between two variables (which may be present even when one variable is a nonlinear function of the other). Other correlation coefficients – such as Spearman's rank correlation
– have been developed to be more robust
than Pearson's, that is, more sensitive to nonlinear relationships.Mutual information
can also be applied to measure dependence between two variables.
Pearson's product-moment coefficient
Example scatterplots of various datasets with various correlation coefficients.
The most familiar measure of dependence between two quantities is the Pearson product-moment correlation coefficient
(PPMCC), or "Pearson's correlation coefficient", commonly called simply "the correlation coefficient". Mathematically, it is defined as the quality of least squares fitting to the original data. It is obtained by taking the ratio of the covariance of the two variables in question of our numerical dataset, normalized to the square root of their variances. Mathematically, one simply divides the covariance
of the two variables by the product of their standard deviations
. Karl Pearson
developed the coefficient from a similar but slightly different idea by Francis Galton
A Pearson product-moment correlation coefficient attempts to establish a line of best fit through a dataset of two variables by essentially laying out the expected values and the resulting Pearson's correlation coefficient indicates how far away the actual dataset is from the expected values. Depending on the sign of our Pearson's correlation coefficient, we can end up with either a negative or positive correlation if there is any sort of relationship between the variables of our data set.
is the expected value
is a widely used alternative notation for the correlation coefficient. The Pearson correlation is defined only if both standard deviations are finite and positive. An alternative formula purely in terms of moments
The correlation coefficient is symmetric:
. This is verified by the commutative property of multiplication.
Correlation and independence
It is a corollary of the Cauchy–Schwarz inequality
that the absolute value
of the Pearson correlation coefficient is not bigger than 1. Therefore, the value of a correlation coefficient ranges between -1 and +1. The correlation coefficient is +1 in the case of a perfect direct (increasing) linear relationship (correlation), −1 in the case of a perfect inverse (decreasing) linear relationship (anti-correlation
and some value in the open interval
in all other cases, indicating the degree of linear dependence
between the variables. As it approaches zero there is less of a relationship (closer to uncorrelated). The closer the coefficient is to either −1 or 1, the stronger the correlation between the variables.
If the variables are independent
, Pearson's correlation coefficient is 0, but the converse is not true because the correlation coefficient detects only linear dependencies between two variables.
For example, suppose the random variable
is symmetrically distributed about zero, and
is completely determined by
, so that
are perfectly dependent, but their correlation is zero; they are uncorrelated
. However, in the special case when
are jointly normal
, uncorrelatedness is equivalent to independence.
Even though uncorrelated data does not necessarily imply independence, one can check if random variables are independent if their mutual information
Sample correlation coefficient
Given a series of measurements of the pair
, the sample correlation coefficient
can be used to estimate the population Pearson correlation
. The sample correlation coefficient is defined as
Equivalent expressions for
If and are results of measurements that contain measurement error, the realistic limits on the correlation coefficient are not −1 to +1 but a smaller range.
For the case of a linear model with a single independent variable, the coefficient of determination (R squared)
is the square of
, Pearson's product-moment coefficient.
Consider the joint probability distribution of
given in the table below.
For this joint distribution, the marginal distributions are:
This yields the following expectations and variances:
Rank correlation coefficients
coefficients, such as Spearman's rank correlation coefficient
and Kendall's rank correlation coefficient (τ)
measure the extent to which, as one variable increases, the other variable tends to increase, without requiring that increase to be represented by a linear relationship. If, as the one variable increases, the other decreases
, the rank correlation coefficients will be negative. It is common to regard these rank correlation coefficients as alternatives to Pearson's coefficient, used either to reduce the amount of calculation or to make the coefficient less sensitive to non-normality in distributions. However, this view has little mathematical basis, as rank correlation coefficients measure a different type of relationship than the Pearson product-moment correlation coefficient
, and are best seen as measures of a different type of association, rather than as an alternative measure of the population correlation coefficient.
To illustrate the nature of rank correlation, and its difference from linear correlation, consider the following four pairs of numbers
(0, 1), (10, 100), (101, 500), (102, 2000).
As we go from each pair to the next pair increases, and so does . This relationship is perfect, in the sense that an increase in is always
accompanied by an increase in . This means that we have a perfect rank correlation, and both Spearman's and Kendall's correlation coefficients are 1, whereas in this example Pearson product-moment correlation coefficient is 0.7544, indicating that the points are far from lying on a straight line. In the same way if always decreases
, the rank correlation coefficients will be −1, while the Pearson product-moment correlation coefficient may or may not be close to −1, depending on how close the points are to a straight line. Although in the extreme cases of perfect rank correlation the two coefficients are both equal (being both +1 or both −1), this is not generally the case, and so values of the two coefficients cannot meaningfully be compared.
For example, for the three pairs (1, 1) (2, 3) (3, 2) Spearman's coefficient is 1/2, while Kendall's coefficient is 1/3.
Other measures of dependence among random variables
The information given by a correlation coefficient is not enough to define the dependence structure between random variables.
The correlation coefficient completely defines the dependence structure only in very particular cases, for example when the distribution is a multivariate normal distribution
. (See diagram above.) In the case of elliptical distributions
it characterizes the (hyper-)ellipses of equal density; however, it does not completely characterize the dependence structure (for example, a multivariate t-distribution
's degrees of freedom determine the level of tail dependence).
was introduced to address the deficiency of Pearson's correlation that it can be zero for dependent random variables; zero distance correlation implies independence.
The Randomized Dependence Coefficient
is a computationally efficient, copula
-based measure of dependence between multivariate random variables. RDC is invariant with respect to non-linear scalings of random variables, is capable of discovering a wide range of functional association patterns and takes value zero at independence.
For two binary variables, the odds ratio
measures their dependence, and takes range non-negative numbers, possibly infinity:
. Related statistics such as Yule's Y
and Yule's Q
normalize this to the correlation-like range
. The odds ratio is generalized by the logistic model
to model cases where the dependent variables are discrete and there may be one or more independent variables.
Sensitivity to the data distribution
The degree of dependence between variables
does not depend on the scale on which the variables are expressed. That is, if we are analyzing the relationship between
, most correlation measures are unaffected by transforming
, where a
, and d
are constants (b
being positive). This is true of some correlation statistics as well as their population analogues. Some correlation statistics, such as the rank correlation coefficient, are also invariant to monotone transformations
of the marginal distributions of
correlation coefficients between
are shown when the two variables' ranges are unrestricted, and when the range of
is restricted to the interval (0,1).
Most correlation measures are sensitive to the manner in which
are sampled. Dependencies tend to be stronger if viewed over a wider range of values. Thus, if we consider the correlation coefficient between the heights of fathers and their sons over all adult males, and compare it to the same correlation coefficient calculated when the fathers are selected to be between 165 cm and 170 cm in height, the correlation will be weaker in the latter case. Several techniques have been developed that attempt to correct for range restriction in one or both variables, and are commonly used in meta-analysis; the most common are Thorndike's case II and case III equations.
Various correlation measures in use may be undefined for certain joint distributions of X
. For example, the Pearson correlation coefficient is defined in terms of moments
, and hence will be undefined if the moments are undefined. Measures of dependence based on quantiles
are always defined. Sample-based statistics intended to estimate population measures of dependence may or may not have desirable statistical properties such as being unbiased
, or asymptotically consistent
, based on the spatial structure of the population from which the data were sampled.
Sensitivity to the data distribution can be used to an advantage. For example, scaled correlation
is designed to use the sensitivity to the range in order to pick out correlations between fast components of time series.
By reducing the range of values in a controlled manner, the correlations on long time scale are filtered out and only the correlations on short time scales are revealed.
The correlation matrix of
. Thus the diagonal entries are all identically unity
. If the measures of correlation used are product-moment coefficients, the correlation matrix is the same as the covariance matrix
of the standardized random variables
. This applies both to the matrix of population correlations (in which case is the population standard deviation), and to the matrix of sample correlations (in which case denotes the sample standard deviation). Consequently, each is necessarily a positive-semidefinite matrix
. Moreover, the correlation matrix is strictly positive definite
if no variable can have all its values exactly generated as a linear function of the values of the others.
The correlation matrix is symmetric because the correlation between
is the same as the correlation between
In statistical modelling
, correlation matrices representing the relationships between variables are categorized into different correlation structures, which are distinguished by factors such as the number of parameters required to estimate them. For example, in an exchangeable
correlation matrix, all pairs of variables are modeled as having the same correlation, so all non-diagonal elements of the matrix are equal to each other. On the other hand, an autoregressive
matrix is often used when variables represent a time series, since correlations are likely to be greater when measurements are closer in time. Other examples include independent, unstructured, M-dependent, and Toeplitz.
Nearest valid correlation matrix
In some applications (e.g., building data models from only partially observed data) one wants to find the "nearest" correlation matrix to an "approximate" correlation matrix (e.g., a matrix which typically lacks semi-definite positiveness due to the way it has been computed).
This sparked interest in the subject, with new theoretical (e.g., computing the nearest correlation matrix with factor structure
) and numerical (e.g. usage the Newton's method
for computing the nearest correlation matrix
) results obtained in the subsequent years.
Uncorrelatedness and independence of stochastic processes
Similarly for two stochastic processes
: If they are independent, then they are uncorrelated.:p. 151
Correlation and causality
The conventional dictum that "correlation does not imply causation
" means that correlation cannot be used by itself to infer a causal relationship between the variables.
This dictum should not be taken to mean that correlations cannot indicate the potential existence of causal relations. However, the causes underlying the correlation, if any, may be indirect and unknown, and high correlations also overlap with identity
), where no causal process exists. Consequently, a correlation between two variables is not a sufficient condition to establish a causal relationship (in either direction).
A correlation between age and height in children is fairly causally transparent, but a correlation between mood and health in people is less so. Does improved mood lead to improved health, or does good health lead to good mood, or both? Or does some other factor underlie both? In other words, a correlation can be taken as evidence for a possible causal relationship, but cannot indicate what the causal relationship, if any, might be.
Simple linear correlations
Four sets of data with the same correlation of 0.816
The Pearson correlation coefficient indicates the strength of a linear
relationship between two variables, but its value generally does not completely characterize their relationship.
In particular, if the conditional mean
, is not linear in
, the correlation coefficient will not fully determine the form of
The adjacent image shows scatter plots
of Anscombe's quartet
, a set of four different pairs of variables created by Francis Anscombe
The four variables have the same mean (7.5), variance (4.12), correlation (0.816) and regression line (y
= 3 + 0.5x
). However, as can be seen on the plots, the distribution of the variables is very different. The first one (top left) seems to be distributed normally, and corresponds to what one would expect when considering two variables correlated and following the assumption of normality. The second one (top right) is not distributed normally; while an obvious relationship between the two variables can be observed, it is not linear. In this case the Pearson correlation coefficient does not indicate that there is an exact functional relationship: only the extent to which that relationship can be approximated by a linear relationship. In the third case (bottom left), the linear relationship is perfect, except for one outlier
which exerts enough influence to lower the correlation coefficient from 1 to 0.816. Finally, the fourth example (bottom right) shows another example when one outlier is enough to produce a high correlation coefficient, even though the relationship between the two variables is not linear.
These examples indicate that the correlation coefficient, as a summary statistic, cannot replace visual examination of the data. The examples are sometimes said to demonstrate that the Pearson correlation assumes that the data follow a normal distribution
, but this is only partially correct.
The Pearson correlation can be accurately calculated for any distribution that has a finite covariance matrix
, which includes most distributions encountered in practice. However, the Pearson correlation coefficient (taken together with the sample mean and variance) is only a sufficient statistic
if the data is drawn from a multivariate normal
distribution. As a result, the Pearson correlation coefficient fully characterizes the relationship between variables if and only if the data are drawn from a multivariate normal distribution.
Bivariate normal distribution
If a pair
of random variables follows a bivariate normal distribution
, the conditional mean
is a linear function of
, and the conditional mean
is a linear function of
. The correlation coefficient
, along with the marginal
means and variances of
, determines this linear relationship:
are the expected values of
, respectively, and
are the standard deviations of
- ^ Croxton, Frederick Emory; Cowden, Dudley Johnstone; Klein, Sidney (1968) Applied General Statistics, Pitman. ISBN 9780273403159 (page 625)
- ^ Dietrich, Cornelius Frank (1991) Uncertainty, Calibration and Probability: The Statistics of Scientific and Industrial Measurement 2nd Edition, A. Higler. ISBN 9780750300605 (Page 331)
- ^ Aitken, Alexander Craig (1957) Statistical Mathematics 8th Edition. Oliver & Boyd. ISBN 9780050013007 (Page 95)
- ^ a b Rodgers, J. L.; Nicewander, W. A. (1988). "Thirteen ways to look at the correlation coefficient". The American Statistician. 42 (1): 59–66. doi:10.1080/00031305.1988.10475524. JSTOR 2685263.
- ^ Dowdy, S. and Wearden, S. (1983). "Statistics for Research", Wiley. ISBN 0-471-08602-9 pp 230
- ^ Francis, DP; Coats AJ; Gibson D (1999). "How high can a correlation coefficient be?". Int J Cardiol. 69 (2): 185–199. doi:10.1016/S0167-5273(99)00028-5.
- ^ a b Yule, G.U and Kendall, M.G. (1950), "An Introduction to the Theory of Statistics", 14th Edition (5th Impression 1968). Charles Griffin & Co. pp 258–270
- ^ Kendall, M. G. (1955) "Rank Correlation Methods", Charles Griffin & Co.
- ^ Mahdavi Damghani B. (2013). "The Non-Misleading Value of Inferred Correlation: An Introduction to the Cointelation Model". Wilmott Magazine. 2013 (67): 50–61. doi:10.1002/wilm.10252.
- ^ Székely, G. J. Rizzo; Bakirov, N. K. (2007). "Measuring and testing independence by correlation of distances". Annals of Statistics. 35 (6): 2769–2794. arXiv:0803.4101. doi:10.1214/009053607000000505.
- ^ Székely, G. J.; Rizzo, M. L. (2009). "Brownian distance covariance". Annals of Applied Statistics. 3 (4): 1233–1303. arXiv:1010.0297. doi:10.1214/09-AOAS312. PMC 2889501. PMID 20574547.
- ^ Lopez-Paz D. and Hennig P. and Schölkopf B. (2013). "The Randomized Dependence Coefficient", "Conference on Neural Information Processing Systems" Reprint
- ^ Thorndike, Robert Ladd (1947). Research problems and techniques (Report No. 3). Washington DC: US Govt. print. off.
- ^ Nikolić, D; Muresan, RC; Feng, W; Singer, W (2012). "Scaled correlation analysis: a better way to compute a cross-correlogram". European Journal of Neuroscience. 35 (5): 1–21. doi:10.1111/j.1460-9568.2011.07987.x. PMID 22324876.
- ^ Higham, Nicholas J. (2002). "Computing the nearest correlation matrix—a problem from finance". IMA Journal of Numerical Analysis. 22 (3): 329–343. CiteSeerX 10.1.1.661.2180. doi:10.1093/imanum/22.3.329.
- ^ "Portfolio Optimizer". portfoliooptimizer.io/. Retrieved 2021-01-30.
- ^ Borsdorf, Rudiger; Higham, Nicholas J.; Raydan, Marcos (2010). "Computing a Nearest Correlation Matrix with Factor Structure". SIAM J. Matrix Anal. Appl. 31 (5): 2603–2622. doi:10.1137/090776718.
- ^ Qi, HOUDUO; Sun, DEFENG (2006). "A quadratically convergent Newton method for computing the nearest correlation matrix". SIAM J. Matrix Anal. Appl. 28 (2): 360–385. doi:10.1137/050624509.
- ^ Park, Kun Il (2018). Fundamentals of Probability and Stochastic Processes with Applications to Communications. Springer. ISBN 978-3-319-68074-3.
- ^ Aldrich, John (1995). "Correlations Genuine and Spurious in Pearson and Yule". Statistical Science. 10 (4): 364–376. doi:10.1214/ss/1177009870. JSTOR 2246135.
- ^ Mahdavi Damghani, Babak (2012). "The Misleading Value of Measured Correlation". Wilmott Magazine. 2012 (1): 64–73. doi:10.1002/wilm.10167.
- ^ Anscombe, Francis J. (1973). "Graphs in statistical analysis". The American Statistician. 27 (1): 17–21. doi:10.2307/2682899. JSTOR 2682899.
Last edited on 13 June 2021, at 00:13
Content is available under CC BY-SA 3.0
unless otherwise noted.