Take the 2-minute tour ×
MathOverflow is a question and answer site for professional mathematicians. It's 100% free, no registration required.

If $X\sim \Gamma(a,\sigma_x^2)$ and $Y\sim \Gamma(b,\sigma_y^2)$. What will be the probability density function of R? Where $R=\frac{X+C}{X+Y}$, here $C$ is a positive constant, $\Gamma(.,.)$ denotes standard gamma probability density function and '$\sim$' represents 'distributed as'. X and Y are independent random variables.

share|improve this question
    
I assumed $S=X+Y$ and find the joint pdf $f_{R,S}(r,s)$. Later, I averaged over S taking limit '0' to 'infinity' and got $f_R(r)$, but not able to find the valid range of R to verify this pdf. –  user8576 Oct 22 '10 at 16:51
1  
More appropriate for math.stackexchange.com, I think –  zhoraster Oct 22 '10 at 17:42
add comment

2 Answers 2

up vote 1 down vote accepted

First of all, since $R=(X+C)/(X+Y)$ (and $X$ and $Y$ are independent gamma variables), then the valid range of $R$ is a priori $(0,\infty)$. The density of $(R,S)$ is given by $f_{R,S} (r,s) = f_X (sr - C)f_Y (s - sr + C)s$, where $f_X$ and $f_Y$ are the densities of $X$ and $Y$ (see the remark below). This leads to $sr-C > 0$ and $s-sr+C > 0$. Thus, $s > C/r$ and $s(r-1) < C$. Hence, if $r > 1$, then $C/r < s < C/(r-1)$, while if $0 < r < 1$, then $C/r < s < \infty$. So, for $0 < r < 1$ you would use $f_R (r) = \int_{C/r}^\infty {f_{R,S} (r,s)\,{\rm d}s}$, and for $r > 1$, $f_R (r) = \int_{C/r}^{C/(r-1)} {f_{R,S} (r,s)\,{\rm d}s}$. In general, a nice expression for $f_R (r)$ is not likely to be found. [Minor point: in view of the title, note that $X+Y$ is, in general, not gamma distributed.]

Remark: As Didier observed, a factor of $s$ was missing in the original expression for $f_{R,S}(r,s)$ (now fixed). The density $f_{R,S}(r,s)$ is found as follows. $(X,Y)$ has density $f_{X,Y}(x,y)=f_X (x) f_Y (y)$. Noting that $X=SR-C$ and $Y=S-SR+C$, it follows by the standard formula for transformation of rv's that $f_{R,S} (r,s)$ is given by $f_{X,Y}(sr-C,s-sr+C)$ times $|J(r,s)|$, where $J(r,s)$ is given by the determinant $\frac{{\partial (sr - C)}}{{\partial r}}\frac{{\partial (s - sr + C)}}{{\partial s}} - \frac{{\partial (sr - C)}}{{\partial s}}\frac{{\partial (s - sr + C)}}{{\partial r}} = s$. Thus, $f_{R,S} (r,s)$ is $s$ times the original expression.

share|improve this answer
    
@Shai: the density $f_{R,S}(r,s)$ is $s$ times what you wrote. –  Did Jan 9 '11 at 17:31
    
Thanks, corrected. –  Shai Covo Jan 10 '11 at 3:35
add comment

The OP asked for the probability density function $f_R$ of $R=(X+C)/(X+Y)$ for a positive $C$. Shai recalled the classical strategy to compute $f_R$ and explained why a nice expression of $f_R$ is unlikely to emerge in the general case.

The limit case $C=0$ is nicer. Then $R=X/(X+Y)$, thus $R\in(0,1)$ almost surely and $$ f_R(r)=\frac{cr^{a-1}(1-r)^{b-1}}{\left(\sigma_y^2r+\sigma_y^2(1-r)\right)^{a+b}}, $$ for a suitable normalizing constant $c$ depending on $(a,b,\sigma_x^2,\sigma_y^2)$.

As expected, if $\sigma_x^2=\sigma_y^2$, $f_R$ is Beta$(a,b)$ density. More generally, $R=T(R_0)$ where $R_0$ is Beta$(a,b)$ and $$ T(r)=\frac{\sigma_x^2r}{\sigma_x^2r+\sigma_y^2(1-r)}. $$

share|improve this answer
add comment

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.