I am new user at this site need help in my research. I want to find the derivative of CDF of inverse gaussian distribution w.r.t. to parameters $\lambda$ and $\mu$. The PDF and CDF of inverse gaussian distribution is given as
$f(x;\lambda, \mu )= \sqrt(\frac{\lambda}{2\pi x^3})e^{- \frac{\lambda(x-\mu^2)}{2\mu^2 x}} , x>0, \lambda>0, \mu>0 $ $ F(x|\lambda, \mu)= \Phi\Bigg[\sqrt{\frac{\lambda}{x}}(\frac{x}{\mu}-1)\Bigg]+ e^\frac{2\lambda}{\mu}\Phi\Bigg[-\sqrt{\frac{\lambda}{x}}(1+\frac{x}{\mu})\Bigg] $
I am working on this problem. I would appreciate it if you would like to give me any help.
Thanks
Dev
$F(x; \lambda, \mu) = \Phi(a)+\Psi \Phi(b)$
where $a = \sqrt{\frac{\lambda}{x}}\left( \frac{x}{\mu}-1 \right) $,$ b = -\sqrt{\frac{\lambda}{x}}\left( \frac{x}{\mu}+1\right)$
$\frac{\partial F}{\partial\mu } = \Phi^{'}(a)\frac{\partial a}{\partial\mu}-\Psi\Phi^{'}(b)\frac{\partial b}{\partial\mu}-\Phi(b)\frac{\partial \Psi}{\partial\mu}$. Is it correct or not ? Please give your comments.
– Dev Jul 06 '17 at 13:19