Intel® oneAPI Math Kernel Library
Ask questions and share information with other developers who use Intel® Math Kernel Library.
Announcements
The Intel sign-in experience has changed to support enhanced security controls. If you sign in, click here for more information.

Expected value? IMSL?

ignacio82
Beginner
156 Views
Hi
Let say I have a function in fortran that is F(X,e1,e2) where e1 e2 are distributedbivariate normal.
Can somebody point me to an example of how to calculate the expected value of F? If it makes it easier I can use IMSL.
Thanks for the help!
0 Kudos
3 Replies
Ron_Green
Moderator
156 Views
I think a better forum for this would be out Math Kernel Library user forum. MKL is bundled with the compiler and perhaps they have a solution.

I will transfer this issue to that forum

ron
Ying_H_Intel
Employee
156 Views
Hello,

Not sure if MKL can help here.
MKL have VSL, which provide function for Random Number Generators,
for example,

vRngGaussian(), Generates normally distributed random numbers.
and

VSL Summary Statistics routines
compute basic statistical estimates for single and double precision multi-dimensional datasets.
for example,
variance-covariance/correlation matrix.

anyway, you may refer the MKL reference manual at
http://software.intel.com/en-us/articles/intel-math-kernel-library-documentation/.

Regards,
Ying H.

mecej4
Black Belt
156 Views
Depending on whether e1 and e2 are independent, in which case there are four random variables, or are dependent, in which case there are two or three random variables, you have to evaluate a two, three or four dimensional integral over the random variables, with ranges from - to +. It may or may not be possible to perform some of the integrations analytically.

The details will depend on the specific functional form of F. It is not clear if X is independent of the random variables.

One of the earliest examples of such a calculation is to be found in calculating the temperature of a gas in terms of the root-mean-square velocity of the molecules (J.C. Maxwell's Kinetic Theory).
Reply