Can someone check my work for this joint denisty function problem

Click For Summary

Homework Help Overview

The problem involves a uniform joint density function for random variables X and Y, defined over a triangular region. Participants are tasked with finding the constant d, the probability p(y

Discussion Character

  • Mixed

Approaches and Questions Raised

  • The original poster attempts to find d by calculating the area of the triangular region and setting up a double integral. They question the correctness of their value for d.
  • Some participants suggest an alternative approach to finding d by noting the area of the triangle and its relation to cumulative probability.
  • For p(y
  • In discussing cov(x,y), the original poster presents their calculations and reasoning, while others suggest considering centroids and balance of areas for a geometric interpretation.

Discussion Status

Contextual Notes

Participants are working within the constraints of a homework assignment, which may limit the information available for the problem. Assumptions about the uniformity of the joint density function and the geometric properties of the triangular region are under discussion.

hwill205
Messages
11
Reaction score
0

Homework Statement



X and Y have uniform joint density function:

f(x,y)= d (constant) for 0<x<1 and 0<y<1-x

1. find d

2. find p(y<x)

3. find cov (x,y)

The Attempt at a Solution



1. For this I first graphed x=1 and y=1 and created a square since x can go from 0 to a maximum of 1 and y also. I then graphed y=1-x. The area of the bottom triangle is what I want. That is 1/2. So i then do a double integral (x goes from 0 to 1 and y goes from 0 to 1-x) of (c dy dx). This should equal 1/2. I get 1/2 c equals 1/2, so c=1. Is that correct?

2. For the p(y<x), I graphed y=x and you get two triangles within the larger one. We want the area of the lower one. We could get this through simple geometry or by using integrals. If you want to use integrals, you have to split the triangle into half and you get a right triangle and a left one.

Area of left one is

Double integral (x goes form 0 to 1/2 and y goes from 0 to x) of 1, which is 1/8

Area of right one is:

Double integral (x goes from 1/2 to 1 and y goes from 0 to 1-x) of 1, which is also 1/8

So the area of the triangle is 1/8+1/8 which is 1/4. This is p(y<x)

3. Cov(x,y)= E(xy)-E(x)E(y)

I got that E(xy) is 1/24

E(x)=1/6
E(y)=1/6

So Cov(x,y) is 1/72.

Can someone please tell this poor, hopeless soul if these answers are even close to being correct.
 
Physics news on Phys.org
for 1) so you set up the integral as
\int dx dy f(x,y) =\int_0^1 dx \int_0^{1-x} dy f(x,y) =d \int_0^1 dx \int_0^{1-x} dy

so you can either integrate or note that the area of the triangle is 1/2, this is what the integral without the d term above will return. Then as this is the cumulative probability, it means d=2 as the total probability to find x,y in the gievn interval must be 1
 
for 2, the geometric solution is easiest, aren't your 2 triangles symmetric, making the probability 1/2
 
for 3, consider the centroids of the main triangle (once again can do by integral but geomtric reasoning will be simpler)

when only considering one direction, the area above must balance the area below
E(x) = E(y) = 1/3

E(xy) will correspond to the centre of mass of the triangle
 

Similar threads

  • · Replies 4 ·
Replies
4
Views
1K
Replies
7
Views
1K
  • · Replies 14 ·
Replies
14
Views
2K
Replies
11
Views
3K
  • · Replies 3 ·
Replies
3
Views
1K
Replies
5
Views
2K
  • · Replies 6 ·
Replies
6
Views
2K
  • · Replies 1 ·
Replies
1
Views
2K
Replies
4
Views
2K
  • · Replies 2 ·
Replies
2
Views
2K