A collection of modeling techniques applied in the design, development and optimization of new products/processes as well as in the improvement of existing products/processes. These methods use a class of designs called Central Composite Designs (CCDs) that model quadratic effects, thus giving an idea of the local shape of the response surface under investigation. Some of the objectives dealt with under RSM:
1. To characterize the behavior of one or more response variables over the region of interest.
2. To find the set of operating conditions that optimizes a response or set of responses.
3. To design products/processes to be robust (insensitive) to environmental or non-controllable conditions.
Central Composite Design
RSM from NIST: - http://www.itl.nist.gov/div898/handbook/pri/section3/pri336.htm