Multiresolution Approximation
DESCRIPTION:
Performs a multiresolution approximation of a signal.
USAGE: 
mra(x, ...)
REQUIRED ARGUMENTS:
x:
a time series object or a dwt object. When x is an object of class "dwt", all the additional arguments will be ignored.
OPTIONAL ARGUMENTS:
...:
additional arguments for dwt. See dwt for details.
VALUE:
an object of class "mra", inheriting from class "decompose". See decompose.object for details.
DETAILS:
Multiresolution analysis can be used to provide a series of coarse to fine approximations based on wavelets at different resolution levels (scales). For details, refer to Chapter 5 of Daubechies (1992) and to the section "Multiresolution Analysis" in the S+WAVELETS User's Manual.

Generic functions crystal.names, print, plot have methods for mra objects.

REFERENCES:
Daubechies, I. (1992). Ten Lectures on Wavelets. SIAM, Philadelphia.

Mallat, S. (1989). A Theory of Multiresolution Signal Decomposition: the Wavelet Representation. IEEE Transactions on Pattern Analysis and Machine Intellingence, 11 (7), 674-693.

SEE ALSO:
decompose.object , dwt , mrd .
EXAMPLES: 
par(mfrow=c(1, 2))
x1 <- make.signal("doppler", n=256)          # noiseless doppler
x2 <- make.signal("doppler", n=256, snr=7)   # noisy doppler
m1 <- mra(x1, wavelet="s8")
m2 <- mra(x2, wavelet="s8")
plot(m1)
plot(m2)