## ⓘ Cokurtosis

In probability theory and statistics, cokurtosis is a measure of how much two random variables change together. Cokurtosis is the fourth standardized cross central moment. If two random variables exhibit a high level of cokurtosis they will tend to undergo extreme positive and negative deviations at the same time.

## 1. Definition

For two random variables X and Y there are three non-trivial cokurtosis statistics

K X, X, X, Y = E is the expected value of X, also known as the mean of X, and σ X {\displaystyle \sigma _{X}} is the standard deviation of X.## 2. Properties

- Kurtosis is a special case of the cokurtosis when the two random variables are identical

- It follows that the sum of two random variables can have kurtosis different from 3 K X + Y ≠ 3 {\displaystyle K_{X+Y}\neq 3} even if both random variables have kurtosis of 3 in isolation K X = 3 {\displaystyle K_{X}=3} and K Y = 3 {\displaystyle K_{Y}=3}.
- The cokurtosis between variables X and Y does not depend on the scale on which the variables are expressed. If we are analyzing the relationship between X and Y, the cokurtosis between X and Y will be the same as the cokurtosis between a + bX and c + dY, where a, b, c and d are constants.

### * 3.1. Examples * Bivariate normal distribution

Let X and Y each be normally distributed with correlation coefficient ρ. The cokurtosis terms are

K X, X, Y, Y = 1 + 2 ρ 2 {\displaystyle KX,X,Y,Y=1+2\rho ^{2}} K X, X, X, Y = K X, Y, Y, Y = 3 ρ {\displaystyle KX,X,X,Y=KX,Y,Y,Y=3\rho }Since the cokurtosis depends only on ρ, which is already completely determined by the lower-degree covariance matrix, the cokurtosis of the bivariate normal distribution contains no new information about the distribution. It is a convenient reference, however, for comparing to other distributions.

### * 3.2. Examples * Nonlinearly correlated normal distributions

Let X be standard normally distributed and Y be the distribution obtained by setting X = Y whenever X 0. In other words, X and Y are both standard normally distributed with the property that they are completely correlated for negative values and uncorrelated apart from sign for positive values. The joint probability density function is

f X, Y x, y = e − x 2 / 2 π H − x δ x − y + 2 H x H y e − y 2 / 2 π) {\displaystyle f_{X,Y}x,y={\frac {e^{-x^{2}/2}}{\sqrt {2\pi }}}\leftH-x\delta x-y+2HxHy{\frac {e^{-y^{2}/2}}{\sqrt {2\pi }}}\right)}where H x is the Heaviside step function and δx is the Dirac delta function. The fourth moments are easily calculated by integrating with respect to this density:

K X, X, Y, Y = 2 {\displaystyle KX,X,Y,Y=2} K X, X, X, Y = K X, Y, Y, Y = 3 2 + 2 π ≈ 2.137 {\displaystyle KX,X,X,Y=KX,Y,Y,Y={\frac {3}{2}}+{\frac {2}{\pi }}\approx 2.137}It is useful to compare this result to what would have been obtained for an ordinary bivariate normal distribution with the usual linear correlation. From integration with respect to density, we find that the linear correlation coefficient of X and Y is

ρ = 1 2 + 1 π ≈ 0.818 {\displaystyle \rho ={\frac {1}{2}}+{\frac {1}{\pi }}\approx 0.818}A bivariate normal distribution with this value of ρ would have K X, X, Y, Y ≈ 2.455 {\displaystyle KX,X,Y,Y\approx 2.455} and K X, X, X, Y ≈ 2.339 {\displaystyle KX,X,X,Y\approx 2.339}. Therefore, all of the cokurtosis terms of this distribution with this nonlinear correlation are smaller than what would have been expected from a bivariate normal distribution with ρ=0.818.

Note that although X and Y are individually standard normally distributed, the distribution of the sum X + Y is platykurtic. The standard deviation of the sum is

σ X + Y = 3 + 2 π {\displaystyle \sigma _{X+Y}={\sqrt {3+{\frac {2}{\pi }}}}}Inserting that and the individual cokurtosis values into the kurtosis sum formula above, we have

K X + Y = 2 π 8 + 15 π 2 + 3 π 2 ≈ 2.654 {\displaystyle K_{X+Y}={\frac {2\pi 8+15\pi}{2+3\pi^{2}}}\approx 2.654}This can also be computed directly from the probability density function of the sum:

f X + Y u = e − u 2 / 8 2 π H − u + e − u 2 / 4 π erf u 2 H u {\displaystyle f_{X+Y}u={\frac {e^{-u^{2}/8}}{2{\sqrt {2\pi }}}}H-u+{\frac {e^{-u^{2}/4}}{\sqrt {\pi }}}\operatorname {erf} \left{\frac {u}{2}}\rightHu}- involving multiple variables. Some examples are covariance, coskewness and cokurtosis While there is a unique covariance, there are multiple co - skewnesses
- not assumed. The cokurtosis between pairs of variables is an order four tensor. For a bivariate normal distribution, the cokurtosis tensor has off - diagonal

Bhatia–Davis inequality |

Combinant |

Comonotonicity |

Concomitant (statistics) |

Conditional probability distribution |

Convolution of probability distributions |

Coskewness |

Hellinger distance |

Infinite divisibility (probability) |

Joint probability distribution |

Khmaladze transformation |

Marginal distribution |

Memorylessness |

Mills ratio |

Neutral vector |

Normalizing constant |

Normally distributed and uncorrelated .. |

Pairwise independence |

Popovicius inequality on variances |

Probability integral transform |

Relationships among probability distr .. |

Shape of a probability distribution |

Smoothness (probability theory) |

Stability (probability) |

Tail dependence |

Truncated distribution |

Truncation (statistics) |

Zero bias transform |

Film |

Television show |

Game |

Sport |

Science |

Hobby |

Travel |

Technology |

Brand |

Outer space |

Cinematography |

Photography |

Music |

Literature |

Theatre |

History |

Transport |

Visual arts |

Recreation |

Politics |

Religion |

Nature |

Fashion |

Subculture |

Animation |

Award |

Interest |