fitHRegLS: LS Fit for Four Parameter Harmonic Regression
In CliffordLai/harper: Harmonic Regression and Periodicity Test

Description Usage Arguments Details Value Author(s) See Also Examples

Estimates mu, A, B and lambda in the harmonic regression, y(t)=mu+A*cos(2*pi*lambda*t)+B*sin(2*pi*lambda*t)+e(t), where e(t) is assumed NID mean zero and constant variance. The default algorithm is enumerative.

1 2	fitHRegLS(z, t = 1:n, K = max(500, floor(length(z)/2)), ncpu = 1, lambdaRange = c(1/n, 0.45), exactQ = FALSE)

`z`	series.
`t`	Time points.
`K`	number of subintervals.
`ncpu`	number of compute nodes for use with parallel.
`lambdaRange`	range of frequencies inside (0,0.5), see Details.
`exactQ,`	default setting is FALSE. It indicates whether nolinear optimizer is used to obtain the final estimate of the frequency.

The QR decomposition is used to efficiently compute the residual sum of squares on the grid. When exactQ=TRUE, a NLS algorithm is used and NLS is indicated in the output title.

list with the following components

coefficients const, A, B, lambda
residuals
periodogram
z
t
K
model
lambdaRange

Yuanhao Lai and A.I. McLeod

qr

z<-c(0.42, 0.89, 1.44, 1.98, 2.21, 2.04, 0.82, 0.62, 0.56, 0.8, 1.33)
fitHRegLS(z)
#
#on multicore pcs, more the package parallel may be used for the
#grid computation but unless n is very large this is not recommended.
## Not run:  #adjust ncpu
system.time(ans1 <- fitHRegLS(z)) #0.06 sec on my computer
system.time(ans2 <- fitHRegLS(z, ncpu=8)) #1.67 sec 
identical(ans1, ans2)

## End(Not run)