This contribution presents an overview of sensitivity analysis of simulation models, including the estimation of gradients. It covers classic designs and their corresponding (meta)models; namely, resolution-III designs including fractional-factorial two-level designs for first-order polynomial metamodels, resolution-IV and resolution-V designs for metamodels augmented with two-factor interactions, and designs for second-degree polynomial metamodels including central composite designs. It also reviews factor screening for simulation models with very many factors, focusing on the so-called "sequential bifurcation" method. Furthermore, it reviews Kriging metamodels and their designs. It mentions that sensitivity analysis may also aim at the optimization of the simulated system, allowing multiple random simulation outputs.