i want to draw ellipse for multivariate data. here is my wish; i have some random numbers x which is
mu=zeros(1,p) % p is dimension var=eye(p) % p is dimension x=mvnrnd(mu,var,n)
and i estimate the location and shape parameter of this data with MCD method. method is not important for you because i don't have any problem. And then
i want draw an ellipsoid with center estimated location parameter and its' border is chi-squre with p degrees of freedom and alfa=0.05. in theory inequality is;
1-) (x-mu)'*inv(var)*(x-mu)<= chi2inv(p,alfa) x element of R1 2-) chi2inv(p,alfa)<(x-mu)'*inv(var)*(x-mu)<= chi2inv(p,sigma) x element of R2 3-) (x-mu)'*inv(var)*(x-mu)> chi2inv(p,sigma) x element of R3
and i want to draw R1,R2 and R3 ellipses. These are three nested ellipses.