Quantum measurements are not deterministic. For this reason quantum measurements are repeated for a number of shots on identically prepared systems. The uncertainty in each measurement depends on the number of shots and the expected outcome of the measurement. This information can be used to improve the fitting of models to quantum measurements. In this paper we analyse ordinary-least squares, weighted least squares and maximum-likelihood estimation. We show that using the information on the quantum measurement uncertainty can lead to improved estimation of system parameters. We also introduce the concept of model violation and demonstrate it can be a valuable tool to analyze model assumptions and performance of quantum systems.