Solution Found!
In Exercise 5.13, the joint density function of Y1 and Y2
Chapter 5, Problem 31E(choose chapter or problem)
In Exercise 5.13, the joint density function of \(Y_{1}\) and \(Y_{2}\) is given by
\(f\left(y_{1}, y_{2}\right)=\left\{\begin{array}{ll} 30 y_{1} y_{2}^{2}, & y_{1}-1 \leq y_{2} \leq 1-y_{1}, 0 \leq y_{1} \leq 1, \\ 0, & \text { elsewhere. } \end{array}\right.\)
a Show that the marginal density of \(Y_{1}\) is a beta density with \(\alpha=2\) and \(\beta=4\).
b Derive the marginal density of \(Y_{2}\).
c Derive the conditional density of \(Y_{2}\) given \(Y_{1}=y_{1}\).
d Find \(P\left(Y_{2}>0 \mid Y_{1}=.75\right)\).
Questions & Answers
QUESTION:
In Exercise 5.13, the joint density function of \(Y_{1}\) and \(Y_{2}\) is given by
\(f\left(y_{1}, y_{2}\right)=\left\{\begin{array}{ll} 30 y_{1} y_{2}^{2}, & y_{1}-1 \leq y_{2} \leq 1-y_{1}, 0 \leq y_{1} \leq 1, \\ 0, & \text { elsewhere. } \end{array}\right.\)
a Show that the marginal density of \(Y_{1}\) is a beta density with \(\alpha=2\) and \(\beta=4\).
b Derive the marginal density of \(Y_{2}\).
c Derive the conditional density of \(Y_{2}\) given \(Y_{1}=y_{1}\).
d Find \(P\left(Y_{2}>0 \mid Y_{1}=.75\right)\).
ANSWER:Step 1 of 4
(a)
Given the Joint probability density function of \({Y_1}\;{\rm{and}}\;{Y_2}\) is,
\(f\left( {{y_1},{y_2}} \right) = \left\{ \begin{array}{l}30{y_1}y_2^2;{y_1} - 1 \le {y_2} \le 1 - {y_1},0 \le {y_1} \le 1\\0;{\rm{otherwise}}\end{array} \right)\).
Let \({Y_1}\;{\rm{and}}\;{Y_2}\) be jointly continuous random variables with joint density function \(f\left( {{y_1},{y_2}} \right)\). Then, the marginal density of \({Y_1}\;{\rm{and}}\;{Y_2}\), respectively, are given by,
\({f_{{Y_1}}}\left( {{y_1}} \right) = \int\limits_{{y_2}} {f\left( {{y_1},{y_2}} \right)d{y_2}} \)
\({f_{{Y_2}}}\left( {{y_2}} \right) = \int\limits_{{y_1}} {f\left( {{y_1},{y_2}} \right)d{y_1}} \)
Hence,
\({f_{{Y_1}}}\left( {{y_1}} \right) = \int_{{y_1} - 1}^{1 - {y_1}} {30{y_1}y_2^2d{y_2}} \)
\({f_{{Y_1}}}\left( {{y_1}} \right) = 30{y_1}\int_{{y_1} - 1}^{1 - {y_1}} {y_2^2d{y_2}} \)
\({f_{{Y_1}}}\left( {{y_1}} \right) = 20{y_1}{\left( {1 - {y_1}} \right)^3},0 \le {y_1} \le 1\)
By the definition,
\(D\left( {\alpha ,\beta } \right) = \frac{{\left| \!{\overline {\, \alpha \,}} \right. \left| \!{\overline {\, \beta \,}} \right. }}{{\left| \!{\overline {\, {\alpha + \beta } \,}} \right. }}\)
Now,
\(D\left( {2,4} \right) = \frac{{\left| \!{\overline {\, 2 \,}} \right. \left| \!{\overline {\, 4 \,}} \right. }}{{\left| \!{\overline {\, {2 + 4} \,}} \right. }}\)
\(D\left( {2,4} \right) = \frac{{\left| \!{\overline {\, 2 \,}} \right. \left| \!{\overline {\, 4 \,}} \right. }}{{\left| \!{\overline {\, 6 \,}} \right. }}\)
\(D\left( {2,4} \right) = \frac{1}{{20}}\)
So,\(\frac{1}{{\beta \left( {2,4} \right)}}y_1^{2 - 1}{\left( {1 - {y_1}} \right)^{4 - 1}} = 20{y_1}{\left( {1 - {y_1}} \right)^3}\).
Hence, the marginal density of \({Y_1}\) is a \(\beta \)-density with \(\alpha = 2\), and \(\beta = 4\).