Scribd
Upload
45 views1 page

3.2 Joint Probability Density Functions: (JPDF) - For Example The JPDF P

Turbulence involves multiple dependent random variables, requiring joint probability density functions (JPDFs) to define the probability of two variables (e.g. u and v) occurring within given ranges simultaneously. JPDFs integrate to 1 over their domain and are positive definite. Marginal probabilities are obtained by integrating the JPDF over one variable. JPDF moments include the covariance, which measures asymmetry and correlation between variables. Variables are uncorrelated if their covariance is zero, but independence requires the JPDF factorizes into the product of individual PDFs.

Uploaded by

224883061
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
45 views1 page

3.2 Joint Probability Density Functions: (JPDF) - For Example The JPDF P

Turbulence involves multiple dependent random variables, requiring joint probability density functions (JPDFs) to define the probability of two variables (e.g. u and v) occurring within given ranges simultaneously. JPDFs integrate to 1 over their domain and are positive definite. Marginal probabilities are obtained by integrating the JPDF over one variable. JPDF moments include the covariance, which measures asymmetry and correlation between variables. Variables are uncorrelated if their covariance is zero, but independence requires the JPDF factorizes into the product of individual PDFs.

Uploaded by

224883061
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

3.

2 Joint probability density functions

Turbulence, of course, involves not one, but several random variables dependent on
each other. Therefore, it is necessary to define joint probability density functions
(JPDF). For example the JPDF PJ (u, v) of variables u and v is the probability of
finding the first random variable between u and u + du, and the second one between
v and v + dv. The integral of PJ over the u,v two-dimensional space is unity by
definition, � ∞� ∞
PJ (u, v) du dv = 1, (3.10)
0 −∞

and PJ (u, v) is positive definite. We recover the PDF of u by integrating PJ over all
values of v, and the PDF of v by integrating over all values of u,
� ∞ � ∞
P (u) = PJ (u, v) dv, P (v) = PJ (u, v) du. (3.11)
−∞ −∞

The moments of u and v can therefore be obtained from PJ as well. The joint first
moment of u and v, uv, is defined as,
� ∞ � ∞
uv = uv PJ (u, v) du dv. (3.12)
−∞ −∞

The covariance of u and v is defined as,

C(u, v) = uv − uv = u v  . (3.13)

The covariance of u and v normalized by the rms values of u and v (the square roots
of their variances) is called the correlation function r(u, v) and is used to quantify
the degree of correlation between u and v,

uv  
r(u, v) = � � . (3.14)
u2  v 2 

For perfectly correlated variables, the correlation function is ±1. The covariance is a
measure of the asymmetry of the JPDF.

Two variables whose covariance is zero, or equivalently whose correlation is zero,


are said to be uncorrelated. Notice that two uncorrelated variables need not to be
independent. Statistical independence of two variables requires that the JPDF can
be expressed as the product of the individual PDFs,

PJ (u, v) = P (u)P (v). (3.15)

Thus independent variables are uncorrelated, but the reverse is not true.

You might also like