STATS 100B Homework 2 2022
Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit
STATS 100B Homework 2
2022
Problem 1 (30 pts)
If X is a nonnegative integer-valued random variable, the probability-generating function of X is
defined to be
G(s) = ! skpk
k=0
where pk = P(X = k).
a. Show that
pk = G(s)"
(5 pts)
dG " = E[X]
d2G " = E[X(X − 1)]
(10 pts)
c. Express the probability-generating function in terms of moment-generating function. (5 pts)
d. Find the probability-generating function of the Poisson distribution. (10 pts)
Problem 2 (10 pts)
Show how to find E(XY) from the joint moment-generating function of X and Y .
Hint: use the Taylor expansion of a real function with two variables, which we covered in the lecture and is also available at . . T S .http://mathworldwolframcom/aylorerieshtml
Problem 3 (15 pts)
Use moment-generating functions to show that if X and Y are independent, then Var(aX + bY) = a2Var(X) + b2Var(Y)
Hint: Var(X) = E[X2] − (E[X])2 = M(0) − M(0)2; MX+Y (t) = MX (t)MY (t) if X and Y are independent.
Problem 4 (15 pts)
Use the delta method to find the approximate expressions for the mean and variance of Y = g(X) in terms of µX = E[X] and σ = Var[X] for
a. g(x) = √x (5 pts)
b. g(x) = log(x) (5 pts)
c. g(x) = sin− 1 (x) (5 pts)
Problem 5 (30 pts)
The position of an aircraft relative to an observer on the ground is estimated by measuring its distance r from the observer and the angle θ that the line of sight from the observer to the aircraft makes with the horizontal. Suppose that the measurements, denoted by R and Θ , are subject to random errors and are independent of each other. Suppose Var[R] = σ , and Var[Θ] = σ . The altitude of the aircraft is then estimated to be Y = R sinΘ .
Note that (r, θ) are considered as realizations of (R, Θ) and will be treated as numbers. Here we do not know E[R] and E[Θ].
a. Find an approximate expression for the mean of Y in terms of r , θ , σ and σ . (10 pts)
Hint: use the delta method for the bivariate case; use Taylor expansion at (r, θ); for this problem only, assume E[R] ≈ r and E[Θ] ≈ θ .
b. Find an approximate expression for the variance of Y in terms of r , θ , σ and σ . (10 pts) Hint: use the delta method for the bivariate case; use Taylor expansion at (r, θ).
c. For a given r , at what value of θ is the estimated altitude Y most variable? (10 pts)
Hint: the approximated Var[Y] is a function of (r, θ); another way of saying this question is to find θ to maximize Var[Y] given r .
2022-02-15