결합누적분포함수,joint_cumulative_distribution_function,joint_CDF

// ㄷㄱㄱ Week 8-1
joint_probability : $\text{Pr}[X,Y]$
joint CDF : $F_{X,Y}(x,y)=\text{Pr}[X\le x,Y\le y]$

Joint CDF의 성질들
  1. $0 \le F_{X,Y}(x,y) \le 1$
  2. When $x_1 \le x_2$ and $y_1 \le y_2,$
    $F_{X,Y}(x_1,y_1) \le F_{X,Y}(x_2,y_2)$
  3. $F_{X,Y}(x,\infty)=\text{Pr}[X<x,Y<\infty]=F_X(x)$ ; marginal cdf
  4. $F_{X,Y}(\infty,\infty)=1,$
    $F_{X,Y}(-\infty,-\infty)=0,$
    $F_{X,Y}(-\infty,y)=?$
    $F_{X,Y}(x,-\infty)=?$
    즉 대충… '무한으로 뻗어갈 때' X, Y가 같은 방향이면 1, 반대 방향이면 0, 그 외의 경우는 결정불가능?
  5. $\text{Pr}[x_1 < X \le x_2, \; y_1 < Y \le y_2]$
    $= F_{X,Y}(x_2,y_2)-F_{X,Y}(x_1,y_2) -F_{X,Y}(x_2,y_1) + F_{X,Y}(x_1,y_1)$


확률변수,random_variable $X,Y$ 에 대해, joint CDF
$F_{X,Y}(x,y)=P(X\le x,Y\le y)$
[http]src. 2.4.


For 2-random variable $\mathbb{X}=(X,Y),\;-\infty<x,y<\infty,$
$F_{X,Y}(x_1,y_1)=P_{X,Y}(X\le x_1, Y\le y_1)$
joint cdf of $\mathbb{X}(\text{or }X,Y)$

성질
1. CDF(누적분포함수)이므로 비감소함수.
For $x_1\le x_2 \text{ and } y_1\le y_2,$
$F_{X,Y}(x_1,y_1)\le F_{X,Y}(x_2,y_2)$
2.
$F_{X,Y}(x_1,-\infty)=F_{X,Y}(-\infty,y_1)=0$
and
$F_{X,Y}(\infty,\infty)=1$
3.
$F_X(x_1)=P(X\le x_1)=F_{X,Y}(x_1,\infty)$
$F_Y(y_1)=P(Y\le y_1)=F_{X,Y}(\infty,y_1)$
related; marginal_CDF
4.
$F_{X,Y}:$ continuous from north and east
5.
$P(x_1<X\le x_2,y_1<Y\le y_2)=F_{X,Y}(x_2,y_2)-F_{X,Y}(x_1,y_2)-F_{X,Y}(x_2,y_1)+F_{X,Y}(x_1,y_1)$
이건 2차원 그림을 생각하면 당연.

from 경북대 http://www.kocw.net/home/search/kemView.do?kemId=1279832 4. Joint cdf