Bivariate expected value and variance

Click For Summary
SUMMARY

The discussion centers on the formulas for expected value and variance in the context of bivariate probability density functions, specifically using the example f(x,y) = 2xy for x and y in the range [0, 3]. The correct formula for the expected value of x is E[X] = ∫_{-∞}^{∞} x f_1(x) dx, where f_1(x) is the marginal probability distribution of x. The expected value E[X,Y] refers to the joint expected value, which is not the same as E[XY]. Variance is defined as Var[X] = ∫_{-∞}^{∞} x² f_1(x) dx - (E[X])², while Var[X,Y] requires additional clarification as it is not covered in the provided material.

PREREQUISITES
  • Understanding of bivariate probability density functions
  • Familiarity with marginal probability distributions
  • Knowledge of integration techniques in calculus
  • Concept of joint expected values and variances
NEXT STEPS
  • Research the concept of marginal probability distributions in bivariate contexts
  • Study the derivation of joint expected values, specifically E[X,Y]
  • Learn about variance in bivariate distributions, focusing on Var[X,Y]
  • Explore applications of bivariate distributions in statistical analysis
USEFUL FOR

Students studying statistics, mathematicians focusing on probability theory, and anyone needing clarification on bivariate expected values and variances.

ArcanaNoir
Messages
778
Reaction score
4

Homework Statement



I need to know these formulas to answer the homework problems, but I can't squeeze the forumlas out of the gibberish in the book, so I'm asking for varification of the formulas.

For a bivariate probability density function, for example f(x,y)= 2xy when x and y are between 0 and 3, and 0 elsewhere,

expected value of x: E[X]
expected value of (X,Y)
Variance of x: Var[X]
Var[X,Y]


E[x] = \int_{-\infty }^{\infty }xf_1(x) \: \mathrm{d}x where f_1(x) is the marginal probability distribution of x. Is this correct?

Now, for E[X,Y], do you think the book means the expected value of the product XY? because the only formula it gives here is for the product. So, E[XY]. If they really mean E[X,Y] and not E[XY], then is there a formula for E[X,Y]? I don't have one in my book.

As for Var[X], is it Var[x] = \int_{-\infty }^{\infty }x^2f_1(x) \: \mathrm{d}x -(E[x])^2 ?

And for Var[X,Y], I have no idea, the only formulas I see in my book are for Var[X+Y].

Remember, these are all for bivariate distributions.
 
Physics news on Phys.org
E[X,Y] would be (E[X],E[Y]).
Same for Var[X,Y].

You have the right E[X] and Var[X].
 
Thanks
 

Similar threads

  • · Replies 8 ·
Replies
8
Views
3K
Replies
0
Views
1K
  • · Replies 2 ·
Replies
2
Views
4K
  • · Replies 4 ·
Replies
4
Views
2K
Replies
4
Views
2K
  • · Replies 1 ·
Replies
1
Views
3K
  • · Replies 15 ·
Replies
15
Views
2K
  • · Replies 6 ·
Replies
6
Views
2K
  • · Replies 6 ·
Replies
6
Views
2K
  • · Replies 10 ·
Replies
10
Views
2K