A descriptive account based on the theory as well as principles of smoothing, filtering and prediction techniques has been presented in this book. It aims to provide understanding of classical filtering, prediction techniques and smoothing techniques along with newly developed embellishments for enhancing performance in applications. It describes the domain in a vivid manner for the purpose of serving as a valuable guide for students as well as experts. It extensively discusses minimum-mean-square-error solution construction and asymptotic behavior, continuous-time and discrete-time minimum-variance filtering, minimum-variance filtering results for steady-state problems and continuous-time and discrete-time smoothing. It further elaborates on robust techniques that accommodate uncertainties within problem specifications, parameter estimation, applications of Riccati equations, etc. These afore-mentioned linear techniques have been applied to various nonlinear estimation problems towards the end of the book. Although they have a risk of assurance of optical performance, these mentioned linearizations can be employed in predictors, filters and smoothers. The book serves the objective of imparting practical knowledge amongst students interested in this field.