2
$\begingroup$

I am trying to work out the distribution function of an exponential distribution, whose rate is exponentially distributed. That is suppose $X \sim \exp(\lambda)$ and $\lambda \sim \exp(\mu)$. Find $P(X<x)$.

I suppose I should use the fact that $$P(X<x \mid \lambda)=1-e^{-\lambda x}$$ but this is as good as is gets.

$\endgroup$
1
$\begingroup$

You are almost there. Since you correctly conditioned on the value of $λ$ just apply the law of total probability to account for all possible values of $λ$ \begin{align}P(X<x)&=\int_{λ}P(X<x\mid λ)f_λ(λ)dλ=\int_{0}^{+\infty}(1-e^{-λx})μe^{-μλ}dλ\\[0.2cm]&=\int_{0}^{+\infty}μe^{-μλ}dλ-μ\int_{0}^{+\infty}e^{-(μ+x)λ}dλ=1-\frac{μ}{μ+x}\end{align}

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.