Estimates AR(p) model parameter with lattice algorithm (Burg 1968) 
 for multiple channels. 
 If you have the NaN-tools, LATTICE.M can handle missing values (NaN), 

 [...] = lattice(y [,Pmax [,Mode]]);

 [AR,RC,PE] = lattice(...);
 [MX,PE] = lattice(...);

  INPUT:
 y	signal (one per row), can contain missing values (encoded as NaN)
 Pmax	max. model order (default size(y,2)-1))
 Mode  'BURG' (default) Burg algorithm
	'GEOL' geometric lattice

  OUTPUT
 AR    autoregressive model parameter	
 RC    reflection coefficients (= -PARCOR coefficients)
 PE    remaining error variance
 MX    transformation matrix between ARP and RC (Attention: needs O(p^2) memory)
        AR(:,K) = MX(:, K*(K-1)/2+(1:K)); = MX(:,sum(1:K-1)+(1:K)); 
        RC(:,K) = MX(:,cumsum(1:K));      = MX(:,(1:K).*(2:K+1)/2);

 All input and output parameters are organized in rows, one row 
 corresponds to the parameters of one channel

 see also ACOVF ACORF AR2RC RC2AR DURLEV SUMSKIPNAN 
 
 REFERENCE(S):
  J.P. Burg, "Maximum Entropy Spectral Analysis" Proc. 37th Meeting of the Society of Exp. Geophysiscists, Oklahoma City, OK 1967
  J.P. Burg, "Maximum Entropy Spectral Analysis" PhD-thesis, Dept. of Geophysics, Stanford University, Stanford, CA. 1975.
  P.J. Brockwell and R. A. Davis "Time Series: Theory and Methods", 2nd ed. Springer, 1991.
  S.   Haykin "Adaptive Filter Theory" 3rd ed. Prentice Hall, 1996.
  M.B. Priestley "Spectral Analysis and Time Series" Academic Press, 1981. 
  W.S. Wei "Time Series Analysis" Addison Wesley, 1990.

Package: tsa