sigmasq.est: Estimation of the unknown noise variance

In trambakbanerjee/casp: Coordinate-wise Adaptive Shrinkage Prediction

Estimation of the unknown noise variance

Description

Estimates the unknown noise variance based on the procedure described in Kritchman and Nadler, (2009)

Usage

sigmasq.est(lambdas, numObs, numOfSpikes)

Arguments

lambdas	eigenvalues to which the distribution is fitted
numObs	number of data observations
numOfSpikes	number of spikes in the spike covariance model

Details

This method calculates an unbiased estimate of the noise variance based on the procedure described in Kritchman and Nadler, (2009). It involves solving a couple of nonlinear equations. This function is called by KN.test.

Value

1. sigma.sq - Estimated noise variance

References

Kritchman, S. and Nadler, B., 2009. Non-parametric detection of the number of signals: Hypothesis testing and random matrix theory. IEEE Transactions on Signal Processing, 57(10), pp.3930-3941.

See Also

KN.test

Examples

library(casp)
lambdas<-c(10,8,6,4,rep(1,6))
sigmasq.est(lambdas,100,4)

trambakbanerjee/casp documentation built on Nov. 22, 2022, 7:24 p.m.