Math 300 , Spring 2002, Day40, M, May 6Hit reload to get most current version

Continuing with Two random variables X, Y "jointly distributed".  Ash 8.1
In practice: Two random variables X, Y  measured on the same experiment.
Sample space:  points in x-y space.
   Probability of a region:  sum or integrate over the region.
Continuous (p. 171 ff + Probability Handout) Joint density function f(x, y)--a surface above the base x-y space.
    Probability of a region R  in x-y space= area under f(x,y) and above the region.
The total probability (area) has to = 1.
"Marginal" probability/density function:

- - - - - -  - - - - - -
 Visualizations:  (Mac 110 Black or Gray: Class Materials/Math 300/For300 Class (DPGraph program is in Math 300 folder)
f(x,y) = x+y, 0<x<1, 0<y<1.   Cardboard model.
     fX(x) = x + 1/2, 0<x<1
Probability Handout problem #17:  Density f(x,y) = Cx(1-y), 0<x<1, 0<y<2.
   Found C = 1/2.  Found fX(x) = 2x, 0<x<1.   fY(y) = (1+y)/4, 0<y<2.
--- --- --- --- --- ---
Conditional distributions: Assuming a particular x value is true/known (xo),  what is the distribution of Y?
 Continuous:  same formulas as discrete, integration instead of sums.
   Think of slicing through the joint density at xo--look at f(xo,y)--the slice.
   The conditional density fY|x(y|xo) has the shape of the slice, but the slice may not have area 1.
              If we divide by  fX(xo), it will.
The conditional probability density of Y given xo:
        fY|x(y|xo) = f(xo, y)/fX(xo)
  Conditional Expectation E(Y|xo):The mean y value, when x is a particular fixed value xo.
      Treat xo as a constant and find the Integral  of  y fY|x(y|xo) dy.
    Remember "Regression problem" in statistics:  For a particular xo, predict the "best" y-value.
           ("best" in some sense or other--average, typical...)
       In probability (the abstraction from data), E(Y|xocan play that role.
             Find it for "all" xo's, and graph it on the x-y plane.
--Find the conditional densities and the conditional expectations for the two functions above:
   See DPGraph pictures--slicing x  will give shape of conditional density (files are labeled by formula)
f(x,y) = x(1-y)/2, 0<x<1, 0<y<2.  fX(x) = 2x, 0<x<1.   fY(y) = (1+y)/4, 0<y<2.
f(x,y) = x+y,  0<x<1, 0<y<1.  fX(x) = x + 1/2, 0<x<1
Another? f(x,y) = 2e-x-y , y>x, x>0.
     Caution: if support of f(x,y) isn't rectangular, you have to keep track of possible values of x and y.

Astonishing(?) fact:  IF E(Y|x) is linear in x, it will coincide with the (abstraction of) the  familiar least squares regression line formula.
- - - - - - - - - - - - -
New topic:  Last semester we were told that the sum of two Normal random variables is normal.
     Question:  How would you find the distribution of W = X+Y?  Try it on discrete:  from handout.
             f(x,y) = (x+y)/21, x = 1,2,3, y= 1,2.  (recall sum of 2 dice)  Add on lines x+y=w, or x = w-y.
  (Ch. 6.1 does more of this, including continuous case.  We won't.)

Another new topic:  Joint normal distribution: (handout)
  Correlation coefficient rho = cov(X,Y)/stdev(X)stdev(Y)   (cf. sample correl. coeff.)
    This is also a parameter in the joint normal.  Not coincidentally, it turns out to be the correlation coefficient for X,Y.
     Level curves are ellipses.
      E(Y|x) is line that bisects "vertical" distances inside ellipses.
DPGraph pictures.
--- --- --- --- --- --- --- --- ---
HW:  Read Normal handout.  Catch up?
 
Sievers home
 Math300-Sp02/Day39.htm 
11pm
5/5/02
This page belongs to Sally Sievers who is solely responsible for its content. Please see our statement of responsibility.