An Introduction to Mathematical Statistics and Its Applications (6th Edition)

Published by Pearson
ISBN 10: 0-13411-421-3
ISBN 13: 978-0-13411-421-7

Chapter 3 Random Variables - 3.4 Continuous Random Variables - Questions - Page 136: 15

Answer

a) $\color{blue}{F'_Y(y) =\dfrac{e^{-y}}{(1+e^{-y})^2} \gt 0,\ -\infty\lt y\lt\infty},$ so $F_Y(y)$ is increasing on $-\infty\lt y\lt\infty$. b) $\color{blue}{\lim\limits_{y\ \to\ -\infty}\ F_Y(y)= \dfrac{1}{\infty} = 0}$. c) $\color{blue}{\lim\limits_{y\ \to\ \infty}\ F_Y(y)= \dfrac{1}{1+0} = 1}$. d) $\color{blue}{f_Y(y) = \dfrac{e^{-y}}{(1+e^{-y})^2},\ -\infty\lt y\lt \infty}.$

Work Step by Step

a) $\underline{F_Y(y)\ \text{is increasing}}$ Observe that $\dfrac{dF_Y(y)}{dy} = \dfrac{d}{dy}\left(\dfrac{1}{1+e^{-y}}\right) $ $= \dfrac{d}{dy}(1+e^{-y})^{-1} = -(1+e^{-y})^{-2}(-e^{-y})$ $= \dfrac{e^{-y}}{(1+e^{-y})^2} \gt 0,\ y\in \mathbb{R},$ where we have used the Chain Rule to differentiate. Thus, $\color{blue}{F'_Y(y) =\dfrac{e^{-y}}{(1+e^{-y})^2} \gt 0,\ -\infty\lt y\lt\infty}$, so that $F_Y(y)$ is increasing for $-\infty\lt y\lt \infty$, i.e., since the frist derivative (with respect to $y$) of $F_Y(y)$ is positive on the entire real line, then $F_Y(y)$ must be increasing on the entire real line. b) $\underline{\lim\limits_{y\ \to\ -\infty}\ F_Y(y) = 0}$ $\begin{align*} \lim\limits_{y\ \to\ -\infty}\ F_Y(y) &= \lim\limits_{y\ \to\ -\infty}\ \frac{1}{1+e^{-y}} \\ &= \frac{1}{1+e^{-(-\infty)}} \\ &= \frac{1}{1+e^\infty} \\ &= \frac{1}{1+\infty} \\ &= \frac{1}{\infty} \\ \color{blue}{\lim\limits_{y\ \to\ -\infty}\ F_Y(y)} &\color{blue}{=0}. \end{align*}$ c) $\underline{\lim\limits_{y\ \to\ \infty}\ F_Y(y) = 1}$ $\begin{align*} \lim\limits_{y\ \to\ \infty}\ F_Y(y) &= \lim\limits_{y\ \to\ \infty}\ \frac{1}{1+e^{-y}} \\ &= \frac{1}{1+e^{-\infty}} \\ &= \frac{1}{1+e^\infty} \\ &= \frac{1}{1+0} \\ &= \frac{1}{1} \\ \color{blue}{\lim\limits_{y\ \to\ \infty}\ F_Y(y)} &\color{blue}{=1}. \end{align*}$ d) $\underline{\text{Associated pdf}\ f_Y(y)}$ Since the associated pdf $f_Y(y) = \dfrac{dF_Y(y)}{dy} = F_Y'(y)$, then from part a) above, $\color{blue}{f_Y(y) = \dfrac{e^{-y}}{(1+e^{-y})^2},\ -\infty\lt y\lt \infty}.$
Update this answer!

You can help us out by revising, improving and updating this answer.

Update this answer

After you claim an answer you’ll have 24 hours to send in a draft. An editor will review the submission and either publish your submission or provide feedback.