Expected value of the result of a function when its input parameter is passed from an exponential distribution

137 Views Asked by At

Say we obtain a random number from an exponential distribution with $\lambda = \frac{1}{4}$. The numbers are passed into $f(x) = (2x + 1)(2x - 1)$. How do i find the expected value of the result?

My first assumption was to do $$ E(X) = E(g(\frac{1}{4}e^{-\frac{1}{4}x})) = \dfrac{1}{4}[-2e^{-\frac{1}{4}x}]_{-\infty}^{\infty} - [x]_{-\infty}^{\infty} $$ However that would be incorrect as we would get an infinity.

I came across this, which would imply the right way to solve this problem is $$ E(g(f(x))) = \int_{-\infty}^{\infty} (\frac{1}{4}e^{-\frac{1}{4}x})(2x + 1)(2x - 1) $$ Though I am unsure if that is correct, or why it would be right. Could someone help explain to me if this is the right way to solve it and the intuition behind it?

1

There are 1 best solutions below

4
On BEST ANSWER

The correct expression is $\int_0^{\infty} \frac 1 4 e^{-\frac 1 4 x} (2x+1)(2x-1) \, dx$. This can be evaluated by repeatedly integrating by parts.