Shows peak frequencies estimated using 50 realizations – each of sample size N = 64 – from the process of Equation (537b) (the actual peak frequency is f1 = XXXXXXXXXXThe peak frequencies shown on the...


Shows peak frequencies estimated using 50 realizations – each of sample size N = 64 – from the process of Equation (537b) (the actual peak frequency is f1 = 0.0725). The peak frequencies shown on the horizontal axis are estimated using the AR forward/backward least squares (FBLS) method with order p = 16; i.e., the coefficients from a fitted AR(16) model are used to compute the corresponding SDF estimate, and the peak frequency is the location of the largest value in this estimate. The “Data” part of the website for the book has 1000 downloadable realizations from this process (the first 50 of these are the ones used in Figure 557). For each realization, use the FBLS AR method of orders p = 2, 3, . . . , 32 to obtain 31 different estimates of the peak frequency. For a given p, compute the sample variance and MSE of the 1000 estimates, and plot these quantities versus p (use a logarithm scale for the vertical axis). Comment upon your findings.






May 05, 2022
SOLUTION.PDF

Get Answer To This Question

Related Questions & Answers

More Questions »

Submit New Assignment

Copy and Paste Your Assignment Here