An estimator for Nonlinear system estimation using Jump Matrix Technique is developed. The idea of the Jump Matrix Technique is to break up the nonlinear system into linear and nonlinear subsystems. The linear subsystem projection, during the sampling interval, is on the basis of the transition matrix of the linear subsystem. At each sampling instant, the system variables are updated using an instantaneous "jump" in the values. The estimator for the nonlinear case is developed on the lines of Kalman filter for the linear case. The Jump Matrix technique is used for system simulation for three different nonlinear systems and then estimation of the system state is carried out using the above mentioned estimator. The system response and the estimated states are considered and the effect of change in system noise parameters is observed. Feedback control of nonlinear system response using the estimated state variables is investigated. Two different systems are considered and their responses are changed using feedback of linear combination of the system state variables. / Master of Science