#import "@youwen/zen:0.1.0": * #import "@preview/cetz:0.3.2" #show: zen.with( title: "Homework 6", author: "Youwen Wu", date: "Winter 2025", ) #show figure: it => { pad(y: 10pt, it) } #set enum(spacing: 2em) #let correction = content => { set text(fill: red) box(stroke: 1pt, inset: 5pt, content) } #let subproblems = content => { set enum(numbering: "a)") content } #rect[ Initial score: $16/16$ ] #rect[ #set text(fill: red) Revised score: $16/16$ ] 1. $ M_X (t) = EE[e^(X t)] = sum_(S_X) e^(x t) p_X (x) \ = e^(-6t) 4 / 9 + e^(-2t) 1 / 9 + 2 / 9 (1+e^(3t)) $ 2. We're looking for $EE[e^(X t)]$. $ M_X (t) = integral_(-infinity) e^(x t) dot 1 / 2 e^(-|x|) dif x \ 1 / 2 integral_(-infinity)^0 e^(x t + x) dif x + 1 / 2 integral_0^infinity e^(-x(1-t)) dif x \ = 1 / 2 [1 / (1+t) - 0] - 1 / 2 [0 - 1 / (1-t)] \ = 1 / 2 [1 / (1+t) + 1 / (1-t)] $ Note that the MGF is only defined for $t in (-1,1)$. 3. #subproblems[ 1. Consider the MGF evaluated at 0 $ [(dif M_X (t)) / (dif t)]_(t=0) = [-4 / 3 e^(-4t) + 5 / 6 e^(5t)]_(t=0) = -1 / 2 $ For the variance we evaluate the second derivative instead. $ [(dif^2 M_X (t)) / (dif t^2)]_(t=0) = [16 / 3 e^(-4t) + 25 / 6 e^(5t)]_(t=0) = 19 / 2 $ And then $ "Var"(X) = 19 / 2 - (-1 / 2)^2 = 37 / 4 $ 2. The PMF is $M_X (t) = sum _k e^(k t) p_X (k) = 1/2 + 1/3^(-4t) + 1/6 e^(5t)$ Then $EE[X]$ and $EE[X^2]$ are $ EE[X] = sum_k k dot p_X (k) = -4 / 3 + 5 / 6 = -1 / 2 \ EE[X^2] = sum_k k^2 dot p_X (k) \ = 16 / 3 + 25 / 6 = 19 / 2 $ So indeed our variance and mean match up. ] 4. The MGF is given by $X ~ "Pois"(3)$ $ M_X (t) = e^(3(e^t - 1)) $ So the answer is $ P(X=4) = e^(-3) 3^4 / 4! = 0.16803 $ 5. Let $Y = (X-1)^2$. The support of $Y$ is ${4,1,9}$. The PMF of $Y$ is $ P(Y=4) = 1 / 7 \ P(Y=1) = 2 / 7 \ P(Y=9) = 4 / 7 $ 6. $X ~ "Gamma"(2,1)$ and it has MGF $ M_X (t) = 1 / ((1-t)^2) $