1
$\begingroup$

Let's say you have a distribution function F. According to Intro to Mathematical Statistics (Hogg), the following property holds:

Pr($a < X \leq b$, $c < Y \leq d$) = $F(b,d) - F(b,c) - F(a,d) + F(a,c)$

What is the intuition behind this property, and how can you prove this formula?

Thank you!

$\endgroup$
1
$\begingroup$

Note that $Pr(a < X \leq b, c < Y \leq d) = Pr(a < X \leq b, Y \leq d) - Pr(a <X \leq b, Y \leq c)$. To see why this relationship holds, moves $Pr(a <X \leq b, Y \leq c)$ to the left side of the equality and note that $\{a <X \leq b, Y \leq c\}$ and $\{a < X \leq b, c < Y \leq d\}$ are disjoint events.

Now use this trick again to the $X$ term and you are ready to go~

$\endgroup$
1
$\begingroup$

It is just the Principle of Inclusion and Exclusion.

Consider the quadrants on a Venn Diagram : $~{\bbox[blue]{\Box}~\bbox[white]{\Box}\\\bbox[purple]{\Box}~\bbox[red]{\Box}}$

$$\def\P{\operatorname{\sf P}} \begin{align} \P((X,Y)\in(a;b]{\times}(c;d]) & =\P(\Box) \\[1ex] & = \P\left({\bbox[blue]{\Box}~\bbox[white]{\Box}\\\bbox[purple]{\Box}~\bbox[red]{\Box}}\right)-\P\left({\bbox[blue]{\Box}\\\bbox[purple]{\Box}}\right)-\P({\bbox[purple]{\Box}~\bbox[red]{\Box}})+\P(\bbox[purple]{\Box}) \\[1ex] & = {\P((X,Y)\in(-\infty;b]{\times}(-\infty;d]) \\-\P((X,Y)\in(-\infty;a]{\times}(-\infty;d]) \\ -\P((X,Y)\in(-\infty;b]{\times}(-\infty;c]) \\+\P((X,Y)\in(-\infty;b]{\times}(-\infty;c])} \\[1ex] & = F(b,d)-F(a,d)-F(b,c)+F(a,c)\end{align}$$

$\endgroup$

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.