Estimation theory is a branch of statistics and applied mathematics that deals with time-varying measurements where uncertain noise is unavoidable due to the nature of data acquisition. Estimation theory is required in numerous areas including telecommunications, engineering mechanics (e.g. control theory for dynamic systems), network security, and satellite geodesy. This course provides advanced-level estimation techniques to those requiring data processing skills for estimating the state of a non-linear dynamic system. Fundamentals of satellite orbit determination and satellite-based positioning problems will be used to illuminate such topics as the linearisation of the estimation process, the least squares solution, the minimum variance estimate, maximum likelihood and Bayesian estimation, the batch processor, the sequential estimation algorithm, the extended sequential estimation algorithm, Kalman filtering, state noise compensation algorithm (e.g. the Gauss-Markov process), smoothing techniques, covariance analysis and the probability ellipsoid.