Inferential (or soft) sensors are used in industry to infer the values of imprecisely and rarely measured (or completely unmeasured) variables from variables measured online (e.g., pressures, temperatures). The main challenge, akin to classical model overfitting, in designing an effective inferential sensor is the selection of a correct structure of the sensor. The sensor structure is represented by the number of inputs to the sensor, which correspond to the variables measured online and their (simple) combinations. This work is focused on the design of inferential sensors for product composition of an industrial distillation column in two oil refinery units, a Fluid Catalytic Cracking unit and a Vacuum Gasoil Hydrogenation unit. As the first design step, we use several well-known data pre-treatment (gross error detection) methods and compare the ability of these approaches to indicate systematic errors and outliers in the available industrial data. We then study effectiveness of various methods for design of the inferential sensors taking into account the complexity and accuracy of the resulting model. The effectiveness analysis indicates that the improvements achieved over the current inferential sensors are up to 19%.