STATS 100B Homework 3 2017
Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit
STATS 100B Homework 3
2017
Problem 1 (20 pts)
The volume of a bubble (V) is calculated by measuring the diameter (D) and using the relationship V = D3 . Suppose that the measured diameter has mean µD variance σ . What is the approximate mean and variance of the volume?
Hint: use the delta method.
Problem 2 (15 pts)
Use the moment-generating functions to show that if X follows an exponential distribution, cX(c > 0) does also.
Hint: The MGF of Exponential(λ) is (1 − t)− 1 .
Problem 3 (30 pts)
(1) Show that for i.i.d. random variables X1 , X2 , . . . , Xn following Exponential(λ) distribution, their sum Sn = !1 Xi follows Gamma(n, 1/λ) distribution.
Hint: Use the moment-generating functions of Exponential(λ) (from Problem 2 above) and Gamma(n, 1/λ) (from Homework 1).
(2) Use the central limit theorem to derive the approximate distribution of Sn as n gets large.
Hint: The central limit theorem says that Sn −E[Sn] has an approximate distribution of N(0, 1)
when n is large. To derive the approximate distribution of Sn , you need to calculate E[Sn] and Var(Sn).
Problem 4 (15 pts)
Suppose that X1 , . . . , X20 are independent random variables with density function f(x) = 2x, 0 ≤ x ≤ 1.
Let S20 = X1 + · · · + X20 . Use the central limit theorem to approximate P(S20 ≤ 10).
Note: Express your answer in terms of Φ(·), the CDF of the standard normal distribution N(0, 1), i.e., P(Z ≤ a) = Φ(a) for the random variable Z ∼ N(0, 1).
Hint: The central limit theorem says that S20 −E[S20] has an approximate distribution of N(0, 1)
when n is large. To derive the approximate distribution of S20 , you need to calculate E[S20] and Var(S20) based on the expectations and variances of X1 , . . . , X20 .
Problem 5 (20 pts)
Let n be the average of n values sampled from N(µ , σ2), a normal distribution with mean µ and standard deviation σ , and let c be any positive number.
(1) Express P(µ − c ≤ n ≤ µ + c) in terms of Φ(·), the CDF of the standard normal distribution N(0, 1).
(2) Use the expression to show that P(µ − c ≤ n ≤ µ + c) increases as n gets large.
Hint: In the class/discussion, we have used the MGF to show that n follows a normal distribu- tion. Here you need the mean and variance of that normal distribution.
2022-02-15