Title :
The missing observations theorem and a new proof of Levinson´s recursion
Author :
Therrien, Charles W.
Author_Institution :
Dept. of Electr. & Comput. Eng., Naval Postgraduate Sch., Monterey, CA, USA
Abstract :
A principle of linear mean-square estimation which we call the "missing observations theorem" is presented here and used to provide a simple alternative derivation of Levinson\´s recursion. The derivation leads directly to the lattice form of the prediction error filter and avoids cumbersome matrix partitioning methods typically used in the derivation of the Levinson algorithm.
Keywords :
mean square error methods; recursive estimation; Levinson´s recursion; linear mean-square estimation; missing observations theorem; prediction error filter lattice form; Computer errors; Lattices; Nonlinear filters; Partitioning algorithms; Random variables; Recursive estimation; State estimation; Vectors;
Conference_Titel :
Circuits and Systems, 2005. ISCAS 2005. IEEE International Symposium on
Print_ISBN :
0-7803-8834-8
DOI :
10.1109/ISCAS.2005.1465085