What is Covariance: Definition and 171 Discussions

In probability theory and statistics, covariance is a measure of the joint variability of two random variables. If the greater values of one variable mainly correspond with the greater values of the other variable, and the same holds for the lesser values (that is, the variables tend to show similar behavior), the covariance is positive. In the opposite case, when the greater values of one variable mainly correspond to the lesser values of the other, (that is, the variables tend to show opposite behavior), the covariance is negative. The sign of the covariance therefore shows the tendency in the linear relationship between the variables. The magnitude of the covariance is not easy to interpret because it is not normalized and hence depends on the magnitudes of the variables. The normalized version of the covariance, the correlation coefficient, however, shows by its magnitude the strength of the linear relation.
A distinction must be made between (1) the covariance of two random variables, which is a population parameter that can be seen as a property of the joint probability distribution, and (2) the sample covariance, which in addition to serving as a descriptor of the sample, also serves as an estimated value of the population parameter.

View More On Wikipedia.org
Recent contents Top users
  1. Coffee_

    Contravariant & Covariant Vectors: Electric Field Case

    From what I understood, a vector can be either covariant or contravariant. Which one this is will depend on how the coordinates of this vector transform under a coordinate transformation. Let's take a look at the electric field then: ##\vec{E}=-\nabla{V}##, so here it looks as if the electric...
  2. fezster

    Connection between Lorentz covariance and special relativity

    s2 = t2 - x2 - y2 - z2 This equation is covariant (Lorentz covariance). The interval "s" is invariant (Lorentz invariance). Can you derive everything in special relativity from these facts? Or am I mistaken about that?
  3. T

    Covariance betw scalar amplitude & spectral index in Planck?

    I am reading some of "Planck 2013 results. XXII. Constraints on inflation." The paper is full of values for various inflationary parameters under various models, with their confidence intervals. For instance, in Table 5 on page 13, the authors report that — for a model including both running of...
  4. SpiderET

    Lorenz covariance vs proofs of relativity theory

    I have been studying history of relativity theory and now it seems to me, that it is wrong to automatically assume that proofs of Lorentz covariance are proofs of Special relativity theory. It seems to me, that there is broader group of theories, that are compatible with Lorentz covariance but...
  5. ElijahRockers

    Calculating Covariance with a Random Vector

    Homework Statement Let ##X## be a random variable such that ##\mu_X = 0## and ##K_{XX} = I##. Find ##Cov(a^T X, b^T X)## for ##a = (1, 1, 0, 0)## and ##b = (0, 1, 1, 0)##. The Attempt at a Solution I guess I am assuming that ##X## is a 4 element random vector. I can't know values of the random...
  6. D

    Parallel Transport & Covariant Derivative: Overview

    I have been reading section 3.1 of Wald's GR book in which he introduces the notion of a covariant derivative. As I understand, this is introduced as the (partial) derivative operators \partial_{a} are dependent on the coordinate system one chooses and thus not naturally associated with the...
  7. I

    MHB Find the expectation and covariance of a stochastic process

    The problem is:Let $W(t)$, $t ≥ 0$, be a standard Wiener process. Define a new stochastic process $Z(t)$ as $Z(t)=e^{W(t)-(1/2)\cdot t}$, $t≥ 0$. Show that $\mathbb{E}[Z(t)] = 1$ and use this result to compute the covariance function of $Z(t)$. I wonder how to compute and start with the...
  8. W

    What Are the Constraints of a Valid Covariance Matrix?

    I'm trying to understand what makes a valid covariance matrix valid. Wikipedia tells me all covariance matrices are positive semidefinite (and, in fact, they're positive definite unless one signal is an exact linear combination of others). I don't have a very good idea of what this means in...
  9. jk22

    Variation on Quantum cross covariance and CHSH

    I tried another approach to the problem of covariance like in Bell's theorem :from the definition ##Cov(A,B)=\langle\Psi|A\otimes B|\Psi\rangle-\langle\Psi|A\otimes 1|\Psi\rangle\langle\Psi|1\otimes B|\Psi\rangle## (##A=diag(1,-1)=B##) we can see that this 'average' is in fact a quadratic form...
  10. T

    MHB Covariance and Correlation matrix

    I would love to learn more about those two matrices. What do they tell us,how to calculate them? Maybe in R Studio? I was searching for some good explanations on google,but i didnt find them. And another question,i apologize if is not in right forum... How do i know how much dispersion can i...
  11. T

    Proving the Property of Covariance Function: (r(n)-r(m))^2≤2r(0)(r(0-r(n-m)))

    Hi all. My task is to prove the property of covariance function: ##(r(n)-r(m))^2≤2r(0)(r(0-r(n-m)))## My solution: ##1) (r(n)-r(m))^2=r(n)^2-2r(n)r(m)+r(m)^2## ##2) 2r(0)(r(0)-r(n-m)))=2r(0)^2-2r(0)r(n-m)## From covariance function properties I know that ##2r(0)^2≥r(n)^2+r(m)^2## So now I...
  12. A

    MHB Proof that covariance matrix is positive semidefinite

    Hello, i am having a hard time understanding the proof that a covariance matrix is "positive semidefinite" ... i found a numbe of different proofs on the web, but they are all far too complicated / and/ or not enogh detailed for me. Such as in the last anser of the link : probability -...
  13. J

    Deriving Covariance between S and N: E(SN) - ìXìN

    consider the following model for aggregate claim amounts S: S=X1+X2+...+XN where the Xi are independent, identically distributed random variables representing individual claim amounts and N is a random variable,independent of the Xi and representing the number of claims.let X has ìx and...
  14. jk22

    Sum of the probabilities equals 3 in bipartite covariance ?

    If we consider a bipartite system as in EPRB experiment we get the probabilities : p(++)=p(--)=1/4*(1-cos(theta)) p(+-)=p(-+)=1/4*(1+cos(theta)) p(+A)=p(+B)=p(-A)=p(-B)=1/2 Thus the sum of all the probabilities equals 3... How does that come ? Is it because in fact there are only...
  15. C

    Random vector mean and covariance

    Homework Statement Random vector Y = [Y_1 Y_2 Y_3 …. Y_m]' where ' = transpose mean = u and and ∑ = covariance Z = N_1 * Y_1 + N_2 * Y_2 + …. + N_m*Y_m all N are numbers Find the covariance of Z E[ (Y- E[Y] )(Y - E[Y] ) ] = E[YY'] -E[Y]E[Y]'= [N_1 N_2 .. N_m] [∑ - u^2 ….∑ -u^2] ' This...
  16. P

    Covariance matrix does not always exist?

    Hey guys. I am going through the PRM (risk manager) material and there is a sample question that is bugging me. The PRM forum is relatively dead, and they don't usually go that deep into the theory anyway. So wanted to ask you guys. Shouldn't a random vector always have a covariance matrix? Why...
  17. T

    Calculating a covariance matrix with missing data

    Consider a co-variance matrix A such that each element ai,j = E(Xi Xj) - E(Xi) E(Xj) where Xi,Xj are random variables. Consider the case that each variable X has a different sample size. Let's say that Xi contains the elements xi,1, …, xi,N, and Xj contains the elements xj,1, ..., xj,n where...
  18. K

    Covariance involving Expectation

    Homework Statement Suppose ##X,Y## are random variables and ##\varepsilon = Y - E(Y|X)##. Show that ##Cov(\varepsilon , E(Y|X)) = 0##. Homework Equations ##E(\varepsilon) = E(\varepsilon | X) = 0## ##E(Y^2) < \infty## The Attempt at a Solution ##Cov(\varepsilon , E(Y|X)) =...
  19. K

    What can we say about Covariance?

    I'm working on a problem that wants me to show that $$Cov(X,Y) = 0$$ and I am up to the point where I simplified it down to $$Cov(X,Y) = E(XY)$$. In other words, $$E(X)E(Y) = 0$$ to make the above true. My question is, what can we conclude if we have that the covariance of two random variables...
  20. E

    Covariance between functions of 3 random variables

    Find cov(Y,Z) where Y = 2X_1 - 3X_2 + 4X_3 and Z = X_1 + 2X_2 - X_3 Information given E(X_1) =4 E(X_2) = 9 E(X_3) = 5 E(Y) = -7 E(Z) = 26 I tried expanding cov(Y,Z) = E(YZ) - E(Y)E(Z) but can't figure out how to calculate E(YZ)
  21. G

    Calculating covariance from variances

    Homework Statement Suppose that X1, X2, and X3 are independent random variables with variances 3, 4, and 8, respectively. Let Y1 = 2X1 + 3X2, Y2 = X3 – X2, and Y3 = X1 + X2 + X3. (a) Using the general relationship Cov(W+X, Y+Z) = Cov(W,Y) + Cov(W, Z) + Cov(X, Y) + Cov(X, Z), find...
  22. D

    The sample covariance of N observations of K

    http://en.wikipedia.org/wiki/Covariance I read from the above link that- The sample covariance of N observations of K variables is the K-by-K matrix. I am wondering- Should "K-by-K" be "N-by-K" or not?
  23. D

    How Does the Covariance Matrix Apply to Vectors X and Y?

    if X= (3, 5, 7) & Y = (2, 4, 1) What is the 3x3 covariance matrix for X & Y?
  24. E

    Sample mean and sample covariance

    Let xij be the ith independently drawn observation (i=1,...,N) on the jth random variable (j=1,...,K). These observations can be arranged into N column vectors, each with K entries, with the K ×1 column vector giving the ith observations of all variables being denoted xi (i=1,...,N). I have...
  25. dexterdev

    MATLAB How to find covariance matrix of 3 or more vectors in matlab?

    Hi all, I know how to find covariance of 2 vectors and variance too. If covariance matrix is to be found of 3 vectors x,y and z, then then the cov matrix is given by cov_matrix(x,y,z) =[var(x) cov(x,y) cov(x,z); cov(x,y) var(y) cov(y,z); cov(x,z) cov(y,z) var(z) ]; Is this...
  26. dexterdev

    Physical significance of eigen vectors of Covariance matrix

    Hi all, I have a doubt regarding the physical significance of eigen vectors of the covariance matrix. I came to know that eigen vectors of covariance matrix are the principal components for dimensionality reduction etc, but how to prove it?
  27. S

    General covariance vs. locality

    hi i read an article by S.carlip about quantum gravity, arXiv:gr-qc/0108040v1 , in this article carlip stated: why we need quantum gravity what's problems of quantum gravity and two ways of quantization of GR. I couldn't realize some clues in section of "the problems of quantum gravity"...
  28. C

    Covariance Matrix of a Vector Random Variable w/ Components Related

    Homework Statement Given X=ZU+Y where (i) U,X,Y, and Z are random variables (ii) U~N(0,1) (iii) U is independent of Z and Y (iv) f(z) = \frac{3}{4} z2 if 1 \leq z \leq 2 , f(z)=0 otherwise (v) fY|Z=z(y) = ze-zy (i.e. Y depends conditionally on...
  29. marcus

    Quant. stat. mech. based on general covariance (BHR's paper)

    Bianchi Haggard Rovelli just posted a landmark paper showing that QSM rises automatically from the GR requirement of general covariance. Yesterday in another thread Atyy identified their paper as especially interesting. I agree. http://arxiv.org/abs/1306.5206 The boundary is mixed Eugenio...
  30. P

    Solving Covariance: X and Y Binomial Variance

    Hi, Homework Statement A fair die is rolled n times. X denotes the number of times '1' is obtained. Y denotes the number of times '6' is obtained. I am first asked to state how X and Y are distributed (marginally) and to find their variance.Homework Equations The Attempt at a Solution Aren't X...
  31. P

    Does Covariance Remain Unchanged Under Variable Transformations?

    Let X1 and Y1 be two random variables. We have Cov(X1,Y1) = 0. Does this extend to any transformation X2 = g(X1) and Y2 = g(Y1), such that Cov(X2,Y2)? Here, g is a continuous function. For example, if we set X2 = X1^2 and Y2 = Y1^2. Do we then from Cov(X1,Y1) = 0 that Cov(X1^2,Y1^2) = 0?
  32. jegues

    Covariance of two dependent variables

    Homework Statement See figure attached Homework Equations The Attempt at a Solution I am not concerned with part (a), I have deduced that indeed X and Y are dependent. I'm not sure if I have done part (b) correctly, and I am quite certain I have done part (c) incorrectly, but...
  33. B

    Expectation of Covariance Estimate

    So I'm trying to take the expectation of the covariance estimate. I'm stuck at this point. I know I have to separate the instances where i=j for the terms of the form E[XiYj], but I'm not quite sure how to in this instance. The answer at the end should be biased, and I'm trying to...
  34. G

    Block of a covariance matrix

    Hello everybody, I’d like to present this math problem that I’ve trying to solve… This matter is important because the covariance matrix is widely use and this leads to new interpretations of the cross covariance matrices. Considering the following covariance block matrix ...
  35. O

    MHB Significance of the Eigenvalues of a covariance matrix

    Hello everyone! I'm curious to know what is the significance of the Eigenvalues of a covariance matrix. I'm not interested to find an answer in terms of PCA (as you of you may be familiar with the term). I'm thinking of a Gaussian vector, whose variance represent some notion of power or...
  36. jk22

    Uncovering Uncertainty: The Experimental Covariance Curve for Entangled Photons

    Some experimental covariance curve for entangled photons gives abs(Cov(0)) less than 1. For example : Violation of Bell inequalities by photons more than 10km apart by Gisin's group in Geneva. Does this mean that experimentally we can't predict with certainty in this case ? In order to...
  37. T

    Are Spinors Truly Invariant Under Coordinate Transformations Beyond Lorentz?

    Is the Dirac Equation generally covariant and if not, what is the accepted version that is? For general coordinate changes beyond just Lorentz, how do spinous transform?
  38. V

    What is the significance of manifest Lorentz covariance for field theories?

    My question is: what does "manifest" Lorentz covariance means for a field theory, as opposed to simply Lorentz invariance. Thanks for the replies!
  39. W

    MATLAB Estimating the variance of eigenvalues of sample covariance matrices in Matlab

    I am trying to investigate the statistical variance of the eigenvalues of sample covariance matrices using Matlab. To clarify, each sample covariance matrix, \hat{\mathbb{R}}_{nn}, is constructed from a finite number, N, of vector snapshots, each sized (L_{vec} \times 1) (afflicted with random...
  40. M

    Covariance of Maxwell Eqn. - conceptual question

    Hey all, This has been bugging me for quite a while now. My question is essentially about how one shows that Maxwell equations are invariant under Lorentz transforms. Writing them in index notation, it is usually appealed to that all terms involved are Lorentz tensors (or contractions thereof)...
  41. zonde

    Understanding General Covariance & Relativity Principle

    I am trying to understand what exactly general covariance states. As I understand general covariance appeared as generalization of relativity principle so I will try to state relativity principle in a manner that I consider more convenient for my purpose. So let's say we have inertial...
  42. T

    Dimensions of Covariance matrix (multiple observations)

    Suppose we have a mxn matrix, where each row is an observation and each column is a variable. The (i,j)-element of its covariance matrix is \mathrm{E}\begin{bmatrix}(\vec{X_i} - \vec{\mu_i})^t*(\vec{X_j} - \vec{\mu_j})\end{bmatrix}, where \vec{X_i} is the column vector corresponding to a...
  43. S

    Covariance - Bernoulli Distribution

    1. Consider the random variables X,Y where X~B(1,p) and f(y|x=0) = 1/2 0<y<2 f(y|x=1) = 1 0<y<1 Find cov(x,y) Homework Equations Cov(x,y) = E(XY) - E(X)E(Y) = E[(x-E(x))(y-E(y))] E(XY)=E[XE(Y|X)] The Attempt at a Solution E(X) = p (known since it's Bernoulli, can also...
  44. iVenky

    How does covariance and correlation coefficient actually work?

    We all know that if the covariance is positive then it means that if one increases then the other one also increases. If the covariance is negative it is the other way round. I know to calculate the covariance and deduce the relation between them. But I don't get an intuitive feeling regarding...
  45. ShayanJ

    Lorentz covariance and Noether's theorem

    Not sure its in the right place or not.If its not,sorry. The relativity postulate of special relativity says that all physical equations should remain invariant under lorentz transformations And that includes Lagrangian too. So it seems we have a symmetry(which is continuous),So by Noether's...
  46. O

    Mahalanobis Distance using Eigen-Values of the Covariance Matrix

    Given the formula of Mahalanobis Distance: D^2_M = (\mathbf{x} - \mathbf{\mu})^T \mathbf{S}^{-1} (\mathbf{x} - \mathbf{\mu}) If I simplify the above expression using Eigen-value decomposition (EVD) of the Covariance Matrix: S = \mathbf{P} \Lambda \mathbf{P}^T Then, D^2_M =...
  47. V

    MATLAB Generating covariance matrices as defined in MATLAB

    Hi, I'm fairly new to MATLAB and I was wondering if you guys could help me out. If I have an N*N matrix, C where the (k,l)-entry is defined as: http://a3.sphotos.ak.fbcdn.net/hphotos-ak-ash3/556394_10151031836051952_2120388553_n.jpg Where x_i is from an N-vector where x_i is normally...
  48. O

    MHB Solving Minimization Problem Involving Variance & Covariance

    Hello Everyone! What $b$ minimizes $E[(X-b)^2]$ where $b$ is some constant, isn't it $b=E[X]$? Is it right to go about the proof as follows: $E[(X-b)^2] = E[(X^2+b^2-2bX)] = E[X^2] + E[b^2]-2bE[X]$, but $E[b] = b$, we differentiate with respect to $b$ and set to zero, we obtain that $b=E[X]$...
  49. F

    Finding covariance using the joint pdf

    The following question appeared on a practice exam: For f(x,y) = 24xy if 0<x+y<1 , 0<x,y 0 elsewhere find Cov(X,Y) I used Cov(X,Y) = E(XY) - E(X)E(Y) to calculate covariance, with E(XY) = \int^{1}_{0}\int^{1-y}_{0}24x^{2}y^{2}dxdy but for some reason I didn't get the...
  50. M

    Gauge invariance Vs. Gauge covariance

    I know what gauge invariance is, but I'm not sure what gauge covariance is. Is it that a given field has a gauge covariant derivative? And under which circumstances do we get a field that is gauge invariant but not gauge covariant? And I would appreciate an example (other than the one...
Back
Top