2. (a) Let {Xt} be the process nt + B sin 6 at Xt = A cos t = 0,±1, ., 6 where A and B are uncorrelated normal random variables with mean 0 and variance 2. Find the best estimate of X5 in terms of X3 and X4. (b) Let X1, X2, X4, X5 be observations from the MA(1) model Xt = Zt – 2Zt-1, {Z}} ~ WN(0, 2). Find the best linear estimate of X3 in terms of X1, X2 and X5 and find its mean squared error.

2. (a) Let {Xt} be the process nt + B sin 6 at Xt = A cos t = 0,±1, ., 6 where A and B are uncorrelated normal random variables with mean 0 and variance 2. Find the best estimate of X5 in terms of X3 and X4. (b) Let X1, X2, X4, X5 be observations from the MA(1) model Xt = Zt – 2Zt-1, {Z}} ~ WN(0, 2). Find the best linear estimate of X3 in terms of X1, X2 and X5 and find its mean squared error.

MATLAB: An Introduction with Applications

6th Edition

ISBN:9781119256830

Author:Amos Gilat

Publisher:Amos Gilat

Chapter1: Starting With Matlab

Section: Chapter Questions

Problem 1P

See similar textbooks

Similar questions

If i have a variable Sigma for standard deviation and Z(T) which is a wiener process. If we take expectation of the formula below, what is the outcome if we follow a normal distribution. My text book says the variable becomes (1/2*Var) Sigma = Standard deviation Z(T) = Wiener process E_0(Sigma*Z(T))
Suppose that the response y is generated by y = f(x) + €, where e is a zero-mean Gaussian noise with variance 1. a) Suppose that f(x) = x. Randomly generate 10 x's and generate the corresponding y's; you need to generate two random numbers (i.e., x and e for each of the 10 points). Fit the data with linear regression and plot the scatter points. b) Suppose that f(x) = x². Randomly generate 10 (x, y) pairs. Fit the data with linear regression and plot the scatter points. c) Suppose that f(x) = 1/x. Randomly generate 10 (x, y) pairs. Fit the data with linear regression and plot the scatter points.
A somewhat outdated study indicates that the mean number of hours worked per week by software developers is 44. We have good reason to suspect that the mean number of hours worked per week by software developers, u, is now greater than 44 and wish to do a statistical test. We select a random sample of software developers and find that the mean of the sample is 47 hours and that the standard deviation is 4 hours. Based on this information, complete the parts below. (a) What are the null hypothesis H, and the alternative hypothesis H, that should be used for the test? H, :0 O
2
Consider the data (1,3), (2,5), (3,9.67) (a) Derive the normal equations for the best fit of the form f(x) = - - + Dx? (b) Find C, D using the normal equations derived above and given data. (c) Find a suitable Linearization for f (x) =- + Dx² (Don't find C, D)
Two random variables X = (1,2) and Y= (-2,-1] are equiprobable and independent. Determine the correlation factor r(X,Y),
Q5 Find the variance for the PDF px(x) = e-«/2, x > 0.
Suppose Y is a random variable with E(Y) = 13 and Var(Y) = 6. Solve for the following: (show complete solution) a. E(3Y+ 10) = ? b. E(Y^2) = ? c. Var (10) = ? d. Var (5) = ?
(1) Let X = b(16, -) find E(4-3x) and distribution function. (2) Let X be a random variable with p.d.f. -2 kx 1
Let X1, X2,...X, be a random sample from f(x,e) = -.0 < x< 8, then T= max(X,} is a %3D complete statistic for the parameter 0 Select one: O True False
Please solved the problem completely.
Let (x1, x2) be i.i.d. samples from a Poisson distribution with unknown parameter > 0. Suppose that we wish to test Ho : λ = 3 versus Ha: λ <3. (a) Consider the test which rejects for T = (x1 + x2₂) < 2. What is the level of significance a? (b) Find the power of this test for λ = 2.