Statistical Signal Processing (EC-654) Assignment-1: Date: 06.02.2018 To Be Submitted by 16.02.2018
Statistical Signal Processing (EC-654) Assignment-1: Date: 06.02.2018 To Be Submitted by 16.02.2018
Assignment-1
Date: 06.02.2018 To be submitted by 16.02.2018
1 N −1
1 N −1
(a) var
N
∑
n=0
x[n] = 2
N
∑ var ( x[n]).
n=0
4 A2 σ 2 2σ 4 1 N −1
( )
(b) var x 2 =
N
+ 2 , where x =
N N
∑ x[n].
n =0
1 N −1 i
∑ n cos ( 2πf0 n + φ) ≈ 0, with i = 0,1, 2.
N i +1 n =0
Specify the necessary assumptions which are to be considered and their feasibility of
acceptance in digital processing of a signal to prove the above.
3. Consider the following signal model
x [ n] = A cos ( 2πf 0 n + φ ) + w [ n]
where n = 0,1,..., ( N − 1) and w → N (0, σ2 ) is additive white Gaussian noise (AWGN).
(a) Find out the Fisher information matrix for vector parameter [ θ] = A φ σ2 .
f0
Here, the parameters not necessarily be all independent to one another, not necessarily
be known or constant. However, the relation for approximation proved in Q.2 may be
applied.
(b) Comment on the significance of the cross diagonal terms in derived Fisher
information matrix.
(c) Finally find inverse of the Fisher information matrix as was derived in 3.(a) and give
CRLB for vector parameter estimate θˆ .
[ Note: Please upload the .pdf file of the prepared material for assignment in Moodle. You
may make .pdf file from the document prepare in computer or .pdf file from the photocopy
taken of handwritten content. File name should be (Assignment#number_RollNo.pdf) for
example:1_115CE0101.pdf]