Small continuous surveys and the Kalman filter

Abstract

Abstract: The time series nature of repeated surveys is seldom taken into account. I present a statistical model of repeated surveys and construct a computationally feasible estimator based on the Kalman filter. The novelty is that the estimator efficiently uses the whole underlying data set. However, for computational purposes, we only need the first and second empirical moments of the data. Keywords: Surveys, Kalman filter, time series.