dependence modelling

Home Forums Data Analysis dependence modelling


This topic contains 3 replies, has 1 voice, and was last updated by  tonjahodges 1 year, 2 months ago.

Viewing 1 post (of 1 total)
  • Author
  • #1541


    I have created the following coding below to generate the probability of an asset defaulting 9 or more times in a year. The underlying theory is using simulations of correlated variable X from a jointly distributed matrix into a gaussian one. How can i get the value of probability of 9 or more defaults?

    Is my approach used in MATLAB correct? i understand the base theory but maybe i am missing something to calculate it in the program?

    N = 30;% Number of assets
    NSimu = 250000; % Number of simulations
    mu = zeros(N,1); % Mean vector
    rho = 0.2;
    S = rho*ones(N) + (1-rho)*eye(N); % Correlation matrix
    r = mvnrnd(mu, S, NSimu);% Correlated X variables
    %Cov=corr(r); % Covariance/Correlation matrix
    U=normcdf(r);%Transforming multivariate to univariate cdf(gaussian).
    h=0.1; %Intensity factor of default
    tau=-log(cdf(‘Normal’,U,0,1))/h; %Calculating default times via gaussian

    %Finding the probability for 9 or more default?? <– Solution required to this

Viewing 1 post (of 1 total)

You must be logged in to reply to this topic.

Bookmark and Share