Abstract:

In this article, the problem on the estimation of the convolution model parameters is considered. The recursive algorithm for estimating model parameters is introduced from the orthogonal procedure of the data, the
convergence of this algorithm is theoretically discussed, and a sufficient condition for the convergence criterion of the orthogonal procedure is given. According to this condition, the recursive algorithm is convergent to model wavelet $\underline{A}=(1,a₁,...,a_q)$.

Key words: Convolution model, parameter estimation, recursive algorithm, norm of operators, convergence