# Find distribution, calculate expected value and variance of two random variables

I am given two random variables $X$ and $Y$, both are independent:

and X distributioN:

-2 -1 3

0.2 0.3 0.5

and Y distribution:

-1 0 2

0.2 0.4 0.4

I have to create distribution and then I have to calculate expected value and variance of $3X - 2Y$, $X^2 + Y^2$, $X \cdot Y$.

I do not understand how to create distribution of $3X - 2Y$, $X^2 + Y^2$ and $X \cdot Y$ accordingly. After creating distribution, I can calculate Expected value and variance, so I think I do not need any special formulas. However, I cannot understand how $3X - 2Y$ and others should be calculated.

Should I take "each $X$" and "each $Y$" and calculate $3X - 2Y$, so there would be 36 items? I do not really understand how this works and what is a meaning of $3X - 2Y$ if $X$ and $Y$ are two random indpendent variables.

-

I'm assuming that you meant $X$ and $Y$ to be independent such that $X$ has probability mass function given by $$P(X=k)= \begin{cases} 0.5 &\quad \text{if }k=3\\ 0.3 &\quad \text{if }k=-1\\ 0.2 &\quad \text{if }k=-2\\ \end{cases}$$ and $Y$ has probability mass function $$P(Y=k)= \begin{cases} 0.4 &\quad \text{if }k=2\\ 0.4 &\quad \text{if }k=0\\ 0.2 &\quad \text{if }k=-1\\ \end{cases}$$ Then using the law of the unconscious statistician we obtain $$E[X]=3\cdot 0.5+(-1)\cdot 0.3+(-2)\cdot 0.2=0.8$$ and similarly $E[Y]=0.6$. By applying the law again, we can also obtain expressions for $E[X^2]$ and $E[Y^2]$. Having them in hand, we can find the variance of $X$ and $Y$ by the formula $$\mathrm{Var}(X)=E[X^2]-E[X]^2$$ and similarly for $Y$.
Now you're able to calculate the mean and variance of $3X-2Y$ by using that $$E[3X-2Y]=3E[X]-2E[Y],$$ and $$\mathrm{Var}(3X-2Y)=3^2\mathrm{Var}(X)+(-2)^2\mathrm{Var}(Y)$$ where we explicitly used that $X$ and $Y$ are independent, see e.g. this.
In a similar manner you can compute the mean and variance of $X^2+Y^2$, but to compute the mean and variance of $X\cdot Y$ you need to use that $$E[g(X)g(Y)]=E[g(X)]\cdot E[g(Y)]$$ for any (measurable) function $g$.
Yes, to find the distribution of e.g. $3X-2Y$ you simply go through all combinations of $(X,Y)$ values. Then you will have to find the probability of $P(3X-2Y=k)$ for $k=-10,-7,-6,-4,-3,-1,5,9,11$. For example$$P(3X-2Y=11)=P(X=3,\,Y=-1)=P(X=3)\cdot P(Y=-1)=0.1,$$ where we have used the independence of $X$ and $Y$. – Stefan Hansen Feb 25 '13 at 6:20
Use the law of the unconscious statistician:$$E[X^2]=3^2\cdot P(X=3)+(-1)^2\cdot P(X=-1)+(-2)^2\cdot P(X=-2)$$ – Stefan Hansen Feb 25 '13 at 8:07