Results 1 to 2 of 2

Math Help - Uncertainty propagation

  1. #1
    Newbie
    Joined
    Sep 2010
    Posts
    1

    Uncertainty propagation

    I have ave a small model running under R. This is basically running various power-law relations on a variable (in this case water level in a river) changing spatially and through time. I'd like to include some kind of error propagation to this.
    My first intention was to use a kind of monte carlo routine and run the model many times by changing the power law parameters. These power laws were obtained by fitting data points under R. I thus have std error associated to them: alpha (ąda) * WaterHight ^ beta (ądb). Is it statistically correct to sample alpha and beta for each run by picking them from a normal distribution centered on alpha (resp. beta) with a standard deviation of da (resp. db) and to perform my statistics (mean and standard deviation of the model result) on the model output?
    It seems to me that da and db are correlated in some way and by doing what I intended to, I would overestimate the final error of my model...
    My statistical skills are rather weak, is there a way people usually deal with this kind of problems?

    Thanks
    Follow Math Help Forum on Facebook and Google+

  2. #2
    Grand Panjandrum
    Joined
    Nov 2005
    From
    someplace
    Posts
    14,972
    Thanks
    4
    Quote Originally Posted by Maayt View Post
    I have ave a small model running under R. This is basically running various power-law relations on a variable (in this case water level in a river) changing spatially and through time. I'd like to include some kind of error propagation to this.
    My first intention was to use a kind of monte carlo routine and run the model many times by changing the power law parameters. These power laws were obtained by fitting data points under R. I thus have std error associated to them: alpha (ąda) * WaterHight ^ beta (ądb). Is it statistically correct to sample alpha and beta for each run by picking them from a normal distribution centered on alpha (resp. beta) with a standard deviation of da (resp. db) and to perform my statistics (mean and standard deviation of the model result) on the model output?
    It seems to me that da and db are correlated in some way and by doing what I intended to, I would overestimate the final error of my model...
    My statistical skills are rather weak, is there a way people usually deal with this kind of problems?

    Thanks
    You need the covariance matrix of (\alpha,\beta) then use that to sample pairs of values from the bivariate normal distribution with the same covariance matrix.

    CB
    Follow Math Help Forum on Facebook and Google+

Similar Math Help Forum Discussions

  1. Error Propagation - Multiplication of xy
    Posted in the Advanced Math Topics Forum
    Replies: 1
    Last Post: October 20th 2011, 11:19 PM
  2. Error propagation
    Posted in the Calculus Forum
    Replies: 3
    Last Post: December 15th 2010, 08:37 AM
  3. Wave propagation
    Posted in the Differential Equations Forum
    Replies: 0
    Last Post: December 15th 2009, 07:00 AM
  4. Finding Absolute Uncertainty From Relative Uncertainty
    Posted in the Advanced Statistics Forum
    Replies: 1
    Last Post: January 16th 2009, 10:16 AM
  5. Error propagation in Physics
    Posted in the Math Topics Forum
    Replies: 0
    Last Post: November 29th 2008, 08:30 AM

Search Tags


/mathhelpforum @mathhelpforum