Practical ways are still needed for optimizing the design of chemical processes, with allowance for uncertain specifications and future changes in economic parameters. This problem fits the two-stage formulation of Dantzig[1]. Unfortunately, we found several practical difficulties in applying this two-stage analysis to realistic process design models. Some of these can be overcome by proper formulation of the process model or by improvements in the computational algotrithm. In the end, we obtained, for two realistic process models, optimal designs with improved flexibility compared to designs based on fixed parameters; the well-known inequalities were satisfied. More generally, the paper includes suggestions for practical efficient use of the two-stage approach in process design. © 1979.