Chebyshev polynomials and least squares estimation based on one-dependent random variables (Q1107936): Difference between revisions

One-dependent random variables appear in several fields of statistical work, e.g. in time series analysis and sampling theory. We consider such random variables \(Y_ 1,...,Y_ k\), \(k\in {\mathbb{N}}\), with \(E(Y_ i)=\mu\), \(i\in \{1,...,k\}\), and regular tridiagonal covariance matrix \(\Sigma\). The real parameter \(\mu\) can be estimated by the method of least squares, which leads to the best linear unbiased estimator \({\hat \mu}{}_{opt}.\) We give representations of \({\hat \mu}{}_{opt}\) and V(\({\hat \mu}{}_{opt})\) in terms of Chebyshev polynomials, which turn out to be a helpful tool in the analysis of structure and properties of \({\hat \mu}{}_{opt}\). Using well-known relations, we give some more sum formulas and formulas concerning products of Chebyshev polynomials, which may also be of interest in other contexts.