A new divide-and-conquer method for estimating the frequency of a single complex sinusoid in additive uncorrelated noise is proposed. Its computational complexity is comparable to previous fast methods (roughly 2N complex multiplies and log2(N) arctangents for N a power of 2). However, it nearly achieves the Cramer-Rao bound for a wider range of input frequency and signal-to-noise-ratio (SNR) v...

We apply the stochastic approximation method to construct a large class of recursive kernel estimators of a probability density, including the one introduced by Hall and Patil (1994). We study the properties of these estimators and compare them with Rosenblatt’s nonrecursive estimator. It turns out that, for pointwise estimation, it is preferable to use the nonrecursive Rosenblatt’s kernel esti...

Estimation is a canonical problem in sensor networks. The intrinsic nature of sensor networks requires estimation algorithms based on sensor data to be distributed and recursive; such algorithms are studied in this chapter for the problem of (conditional) least squares estimation. The chapter is divided into three parts. In the first part, distributed and recursive estimation algorithms are dev...

Article history: Available online xxxx

An account is given of recursive regression and Kalman filtering that gathers the important results and the ideas that lie behind them. It emphasises areas where econometricians have made contributions, including methods for handling the initial-value problem associated with nonstationary processes and algorithms for fixed-interval smoothing.