Probability Integral Transform

Let X have a continious c.d.f $F$, and let $Y = F(X)$.
(This transformation from $X$ to $Y$ is called the probality integral transformation)
The distribution of $Y$ is the uniform distribution on the interval [0, 1]

Let $U$ have the uniform distribution on interval [0, 1], and let $F$ be a continuous c.d.f with quantile $F^{-1}$. Then $X=F^{-1}(U)$ has c.d.f $F$.

proof: Let $X=F^{-1}(U)$. To see that X has c.d.f $F(⋅)$, we want to show that $P(X\leq t)=P(F^{-1}(U)\leq t)=P(U\leq F(t))=F(t)$

Apply $F$ to $F^{-1}(U) \leq t$, since $F$ is increasing. So $U\leq F(t)$

This gives us a method for transforming an arbitrary continuous random variable $X$ into another random variable $Y$ with any desired continuous distribution.

To be specific, let $X$ has a continuous c.d.f $F$, and let $G$ be another continuous c.d.f. Then $U=F(X)$ has the uniform distribution on the interval [0, 1]. $Y=G^{-1}(U)$ has the c.d.f $G$. Combining these, $Y=G^{-1}[F(X)]$ has the c.d.f G.