How to generate N independent, identically distributed random numbers from the Reciprocal Normal Distribution?

How to generate N independent, identically distributed random numbers from the Reciprocal Normal Distribution?

If are IID normally-distributed random numbers, ther reciprocal normal distribution is the probability density function of .

How do I generate N random numbers: from the probablity density function? Does Matlab have a built-in function for those?

https://en.wikipedia.org/wiki/Inverse_distribution#Reciprocal_normal_distribution

Answer 1

[Torsten]

% Generate 10 random numbers from the inverse normal distribution
% (mu=0, sigma=1)
%
% G(y) = 1 - F(1/y) 
% is the cumulative distribution function of the inverse normal distribution 
% if F is the cumulative distribution function of the normal distribution
%
mu = 0;
sigma = 1;
u = rand(10,1);
y = 1./norminv(1-u,mu,sigma)

y = 10×1

0.6546 -0.6856 -1.5412 -1.1754 4.1175 -0.6873 -0.9705 -1.2747 0.4076 1.6827

[MatlabNickname]

@Torsten: Thanks!