I. Estimated evaluation criteria
Suppose a is a characteristic quantity of a generalized stationary random signal x(n), representing an estimator of a. The estimated deviation can reflect the closeness of the estimator to the true value, which is defined as follows:
Intuitively, the smaller B is, the better the estimate of a will be. In theory, when the number of samples N tends to infinity, a gradually unbiased estimate will be formed, as follows:
The variance of the estimate can indicate the degree of dispersion of the estimated values relative to the estimated mean. The estimated variance is defined as follows:
The estimated mean square error can comprehensively reflect the characteristics of the estimate, which is defined as follows:
If the mean square error satisfies the following conditions, it is called a consistent estimate, as follows:
- Number of samples
2. Consensus estimates
Given consistent estimates, show that both bias and variance tend to zero.
The given mean square error simplifies as follows:
Obtained by the condition:
So you can get:
The final available bias and variance are both 0
Using estimates representing one algorithm, estimates for other algorithms are expressed as follows:
If the following inequalities hold constant:
The estimate is called an effective estimate.
3. Estimated mean
Using N to represent the number of observations, the observation samples of the stationary signal sequence x(n) are as follows:
From this an estimate of the mean can be calculated:
3.1 Bias
First available:
From this the deviation can be calculated:
So this method is an unbiased estimate.
3.2 Variance
According to the definition, it can be obtained:
(1) When and are not correlated with each other, there are:
Substituting the original formula for simplification:
So the variance of this estimate is:
The following limit can be obtained:
Therefore, the estimate is unbiased and consistent.
(2) When and are relevant, there are:
Further simplification can be obtained:
When the difference between i and j is m, we can get:
Since there are Nm pairs of data samples separated by m points in the N data, it can be obtained:
When there is correlation in the signal data, the variance of the estimated value is related to the covariance, which is not a consistent estimate. Of course, changing the value of N can improve the estimated variance.
4. Estimated variance
4.1 The mean is known
When the signal mean is known, the variance estimate can be calculated as:
Prove that this formula is an unbiased consistent estimate.
untie:
(1) First verify the deviation:
(2) Then verify the consistency:
So, the estimated variance is calculated as:
4.2 Unknown mean
When the estimated mean is unknown, the estimated value is used instead, and the variance can be estimated as follows:
(1) Prove that the deviation is a biased estimate
(2) Modify the original formula to form an unbiased estimate
untie:
(1)
Obviously this is a biased estimate.
(2) The form of unbiased estimation is as follows:
The following proves that this formula is an unbiased estimate:
Obviously available:
Taking the mean of both sides of the above formula, we can get:
So B=0, this is an unbiased estimate.
5. Estimate autocorrelation function
5.1 Unbiased Autocorrelation Function Estimation
The estimation formula is:
First it can be calculated:
From this the deviation can be calculated as:
So this estimate is an unbiased estimate.
The calculation of the estimated variance is more complicated, and it can be approximated as follows:
When N satisfies the following, the variance tends to 0:
5.2 Estimation of partial autocorrelation function
The estimation formula is as follows:
First it can be calculated:
So the estimated bias is:
Then it can be calculated:
If x(n) is a real Gaussian signal with zero mean, the estimated variance is:
Obviously the following limit can be obtained:
So for a fixed m, y is a consistent estimate of .
The partial autocorrelation function estimation formula finds the Fourier transform:
In order to use FFT to calculate linear convolution, x(n) can be extended to a sequence of 2N-1 points, as follows:
Let l=n+m, can get:
The above formula represents the energy spectrum of a finite signal, and after dividing by N, represents the power spectrum.