Skip to main content
T
Theo_Gagner10-Marble
10-Marble
November 27, 2018
Solved

Determine Relative Contribution of Sources of Variance | Monte Carlo

  • November 27, 2018
  • 3 replies
  • 2585 views

Hello,

 

I have a working simulation worksheet that runs a Monte Carlo analysis on a function.  With the results, I can bin the simulations for the input variables as well as for the output.  I am struggling though, to find references on how I might "tease" out the relative contribution of sources of variance.  

 

Are there any suggestions for using the input function, along with known means and standard deviations of the input variables to establish these values?  

 

Is there an analytical way to look at the result of the Monte Carlo simulations and determine relative variance?

 

Sorry for the abstraction in advance...I attached my Monte Carlo simulation up to this point, but couldn't even begin to try and "mock up" what I am asking for help with.

Best answer by LucMeekes

A little experimenting:

LM_20181128_Variance.png

That's pretty close to the result of your MonteCarlo run's stdev (4300 N)...But no proof!

 

Success!
Luc

3 replies

D
DJF16-Pearl
16-Pearl
November 27, 2018

I can't open your file (5.0?).  But here's a sheet I've posted before that makes a tornado graph to compare contributions.

L
LucMeekes23-Emerald IV
23-Emerald IV
November 28, 2018

You might want to look here

https://en.wikipedia.org/wiki/Variance#Product_of_independent_variables

for information on symbolically/analytically determining the variance of your function result from the variances (and expected values) of its input variables.

 

Success!

Luc

L
LucMeekes23-Emerald IVAnswer
23-Emerald IV
November 28, 2018

A little experimenting:

LM_20181128_Variance.png

That's pretty close to the result of your MonteCarlo run's stdev (4300 N)...But no proof!

 

Success!
Luc

    Terms & ConditionsAccessibility statement