data_segments.m

%DATA_SEGMENTS
%   The aim of time series analysis for segmented data is to obtain
%   a single parametric model for multiple segments of data, that
%   have been generated by the same process.
%
%   Segments of equal length must be arranged in columns:
%   the data sets a(1),...,a(100) and b(1),...,b(100) are written as
%   a 100x2 matrix:
%   x = [a(1)   b(1)
%        a(2)   b(2)
%        ...    ...
%        a(100) b(100)];
%
%   The number of observations for this set of data is written as:
%   n_obs = [100 100];
%
%   Automatic inference for segments of data can be done as follows.
%   Time series analysis of S segments of N observations is performed 
%   as follows:
%   1)  Estimate a high-order AR model using BURG_S;
%   2)  call ARMASEL_RS, with N_OBS = [100 100];
%
%   For segments of unequal length the data is written as a cell array,
%   where each element of the cell array can contain a signal or a
%   number of segments of equal length.
%   Example: Signal a(1),...a(100), b(1),...,b(100) en c(1),...c(1000):
%     x = {[a(1)   b(1)    [c(1)
%           a(2)   b(2)     c(2)
%           ...    ...      ...
%           a(100) b(100)]  ...
%                           ...
%                           c(1000)]}
%
%   Automatic inference for these segments can be done as follows.
%   1)  Estimate a high-order AR model using BURG_SU;
%   2)  call ARMASEL_RS, with N_OBS = [100 100 1000];
%
%   See also: BURG_S, BURG_SU, ARMASEL_RS.