Consider the simple moving average model Xt = 0.02 + Wt − 0.4Wt−1, where Wt is a sequence of i.i.d. normal random variables with mean zero and variance 4. What is the mean of Xt? What is the variance of Xt. Show working
Consider the simple moving average model Xt = 0.02 + Wt − 0.4Wt−1, where Wt is a sequence of i.i.d. normal random variables with mean zero and variance 4. What is the mean of Xt? What is the variance of Xt. Show working
Xt = 0.02 + Wt − 0.4Wt−1
Wt ~ N(0,4)
mean of Xt= E(Xt)
=E( 0.02 + Wt − 0.4Wt−1)
=E(0.02)+E(Wt)-0.4*E(Wt-1)
=0.02+0-0.4*0 since E(constant)=constant
=0.02
mean of Xt=0.02
Variance of Xt= V(Xt)
=V( 0.02 + Wt − 0.4Wt−1)
=V(0.02)+V(Wt)-V(0.4*Wt-1)
=0+4+0.4^2*4 since Var(constant)=0
=4+0.64
=4.64
Answer:
mean of Xt=0.02
Variance of Xt = 4.64
Consider the simple moving average model Xt = 0.02 + Wt − 0.4Wt−1, where Wt is...
Consider the regression model where the εi are i.i.d. N(0,σ2) random variables, for i = 1, 2, . . . , n. (a) (4 points) Show βˆ is normally distributed with mean β and variance σ2 . 1 1SXX Question 6 Consider the regression model y = Bo + B12 + 8 where the €, are i.i.d. N(0,0%) random variables, for i = 1,2, ..., n. (a) (4 points) Show B1 is normally distributed with mean B1 and variances
7. Let Z be Gaussian white noise, i.e. Z is a sequence of i.i.d. normal r.v.s each with mean zero and variance 1. Define Zt, t(-1- 1)/v2, if t is odd Show that Xis WN(0,1) (that is, variables Xt and Xt+k,k2 1, are uncorrelated with mean zero and variance 1) but that Xt and Xi-i are not i.i.d 7. Let Z be Gaussian white noise, i.e. Z is a sequence of i.i.d. normal r.v.s each with mean zero and variance...
Consider the time series of Xt = Xt−1 + Wt, whereWt are i.i.d and Wt ∼ N (0, σ2 ) and X0 = 0. Let X¯ = 1 n Pn i=1 Xi . Derive the general form for var(X¯). (Hint: Pn i=1 i 2 = n(n+1)(2n+1) 6 ) Consider the time series of X-Xi-1+Wi, whereW are i.i.d and W N(0, σ2) and Xo 0. Let X = n Σ, Derive the general form for var(X). (Hint: Σ i- n(n+1)(2n+1))
Consider the time series Consider the time series of Xt Xt-1 + Wt, where Wt ~ N(0, σ2) and Xi. Derive the general form for var(X). (Hint: i=1 5 ? -n(n+1)(2n+1)
Problem 3. (Law of Large Number and Moving Average Model) Let s0, E1, E2, be a sequence of i.i.d. N(0,1) distributed random variable. Define a new sequence of random variables X1, X2, X3,-.. , as: | ; Xn = uEn + O€n-1; 1 Xi, answer the following ques- where and 0 are constant parameters. Define Xn _ =1 n tions: 1) Find out Var(Xn); 2) Show that X >u as n -> c0.
1. An AR(1) process is given by Xų = 0.727-1 + wt, where et represents a sequence of uncorrelated random variables of zero mean and constant variance 0.4 so that Rww 0.48(n). a. If in addition wt is normally distributed then what can we say about the output Xť ? b. Compute the autocorrelation function of the output process.
2. Suppose that Ya ut where the ut are iid Normal with mean zero and variance σ2, but that you mistakenly think Yt is difference stationary. You therefore construct a new series a) Are the Xt i.i.d.? Explain b) Is X stationary? Explain c) Calculate the mean, variance, and autocorrelation function of X d) How does the answer you obtained in (c) compare with the mean, variance and autocor- relation function of Y? 2. Suppose that Ya ut where the...
1. Consider the simple linear regression model: Ү, — Во + B а; + Ei, where 1, . . , En are i.i.d. N(0,02), for i1,2,... ,n. Let b1 = s^y/8r and bo = Y - b1 t be the least squared estimators of B1 and Bo, respectively. We showed in class, that N(B; 02/) Y~N(BoB1 T;o2/n) and bi ~ are uncorrelated, i.e. o{Y;b} We also showed in class that bi and Y 0. = (a) Show that bo is...
2. Consider an ARMA(1,1) process, X4 = 0.5X:-1 +0+ - 0.25a4-1, where az is white noise with zero mean and unit variance. (a) Is the model stationary? Explain your answer briefly. (b) Is the model invertible? Explain your answer briefly. (c) Find the infinite moving-average representation of Xt. Namely, find b; such that X =< 0;&–; j=0 (d) Evaluate the first three lags of the ACF and PACF.
If we fit the following model with n observations where i = 1,...,n and 's are identically and independently distributed as a normal random variable with a mean of zero and a variance , and all the x's are fixed. How can I show that the point estimator of the mean response and its residuals are statistically independent normal random variables? We were unable to transcribe this imageWe were unable to transcribe this imageWe were unable to transcribe this image