Todays Goals - PowerPoint PPT Presentation

1 / 25
About This Presentation
Title:

Todays Goals

Description:

Var(X Y) = Var(X) Var(Y) Cov(X,Y) Var(X-Y) = Var(X) Var(Y) Cov(X,Y) ... Load surveys indicate that the mean and var are the same on all floors. ... – PowerPoint PPT presentation

Number of Views:22
Avg rating:3.0/5.0
Slides: 26
Provided by: mielsvr2
Category:
Tags: goals | todays | var

less

Transcript and Presenter's Notes

Title: Todays Goals


1
Todays Goals
  • Calculate and apply covariance and correlation
  • Calculate linear functions of multiple variables
  • HW 9 (due Wed. April 15) Ch 4 63. Ch 5 22
    30.
  • Article will be due April 24
  • Office hours this week Tu 2-350.

2
Independence
  • Two discrete R.V. are independent if
  • p(x,y) p(x)p(y)
  • Two continuous random variables X and Y are said
    to be independent if for every pair of x and y
    values,
  • f(x,y) fX(x) fY(y).

3
Expected Value
If X and Y are independent random variables,
then EXY EXEY.
4
Different degrees of covariance
5
Covariance
  • Covariance is a measure of how related two
    variables are specifically in a linear
    relationship
  • Cov(X,Y) E(X-mx )(Y-my )
  • short cut
  • If X and Y are independent

6
Correlation
  • The correlation Corr(X,Y) between two random
    variables X and Y is
  • This number is always between -1 and 1
  • If X and Y are independent, Corr(X,Y) 0
  • However, the converse is not true

7
Correlation
Are these variables correlated? Are they
independent?
8
Example find correlation between HW and midterm
9
Example find correlation
  • cov EXY EXEY

Sd .13 .24
10
The correlation coefficient between midterm
grades and HW scores is 0.14
11
Independence
  • Two discrete R.V. are independent if
  • p(x,y) p(x)p(y)
  • Two continuous random variables X and Y are said
    to be independent if for every pair of x and y
    values,
  • f(x,y) fX(x) fY(y).
  • If two RV are independent, then COVX,Y 0 and
    EXY EXEY

12
Expected Value of a sum
  • Regardless of covariance
  • EXYEXEY

13
Variance of a sum or difference
  • Var(XY) Var(X)Var(Y)Cov(X,Y)
  • Var(X-Y) Var(X)Var(Y)Cov(X,Y)
  • If X and Y are independent then
  • Var(XY) Var(X)Var(Y)
  • Var(X-Y) Var(X)Var(Y)

14
Are X and Y independent? T yes, Fno
p(0,0) .02 ? .2 .07 .014 p(0)p(0)
15
What is EXY?
EX 5.55 EY 8.55
16
What is EXY? EXY EXEY
EX 5.55 EY 8.55
17
True or False EMax(X,Y) 8.55
EX 5.55 EY 8.55
18
True or False EMax(X,Y) 8.55
EX 5.55 EY 8.55
Max is not a linear function, so the flaw of
averages applies
19
Correlation Proposition
  • If a and c are either both positive or both
    negative, Corr(aX b, cY d) Corr(X, Y)
  • For any two rvs X and Y,

20
Correlation Proposition
  • If X and Y are independent, then
    but does not imply independence.

  • for some numbers a and b with

21
Expected Value and Variance of a sum of random
variables
22
Example building design
  • The vertical load on the ground-floor columns of
    an n-story building is the sum of the indivual
    loads
  • Load surveys indicate that the mean and var are
    the same on all floors. What is mean and variance
    of Y?

23
Example building design
  • The vertical load on the ground-floor columns of
    an n-story building is the sum of the individual
    loads
  • Load surveys indicate that the mean and var are
    the same on all floors, so
  • EY nmx

24
Example building design
  • We design the building to be safe, that is we
    design it to take a load L so that P(YgtL) is very
    small, say .001.
  • What happens if we assume independence between
    the loads on different floors? What if the loads
    are not independent?

25
Statistics and Statistical Inference
Write a Comment
User Comments (0)
About PowerShow.com