Re: Expected value




No, not that simple.

First find out distribution of Z1=X|Y=D, Z2=X|Y=G

P(Y=D)=0.1+0.1+0.05=0.25
So
Z1=0, p=0.1/0.25=0.4
Z1=1, p=0.1/0.25=0.4
Z1=2, p=0.05/0.25=0.2

And E[Z1]=0*0.4+1*0.4+2*0.2=0.8.

Z2 is similar.

grimster Wrote:
> simple discrete case with this distribution:
>
> X is the rows and Y the columns
> - D - G
> 0 - 0,1 - 0,15
> 1 - 0,1 - 0,3
> 2 - 0,05 - 0,3
>
> i'm supposed to calculate the conditional expected values.
> that is
> E(X|Y=D) and E(X|Y=G)
>
> are the answers 0,1+0,1=0,2 and 0,3+0,6=0,9 ? is it really that
> simple?


--
royfei
------------------------------------------------------------------------
royfei's Profile: http://schools.mylounge.us/member.php?userid=31785
View this thread: http://schools.mylounge.us/showthread.php?t=87239

.



Relevant Pages

  • Re: joint "mixed distribution"
    ... > I am trying to construct a joint probability ... > distribution, where one variable is discrete and ... > continuous to discrete in some way, ... Prev by Date: ...
    (sci.stat.math)
  • Re: Findining a P value from a T distribution
    ... __The probability Bob to fail his purposes is 1. ... WORSE: the distribution is DISCRETE. ... Prev by Date: ...
    (sci.stat.math)
  • Re: Discrete vs Continuous Solution ??
    ... a finite and continuous straight-line extending in the +ve Y-direction ... of the points where the discrete points are ... distribution of the initial discrete points ...
    (sci.math.num-analysis)
  • Re: Anderson-darling test for discrete distribution fitting
    ... have a reasonable formulation for the AD statistic, ... discrete distributions and to tied observations. ... David Jones ... distribution having Ffor its CDF ... ...
    (sci.stat.consult)
  • Re: Skewed differences and paired students t test
    ... > some circumstances) be both discrete and in a small range. ... The null distribution, evaluated this way, would be based on ... careful to calculate the right probability for the significance level: ... pairs is small then you could replace the randomisation by a complete ...
    (sci.stat.math)

Quantcast