SDVOSB * MOB * WOSB 
Design of Experiments (DOE)Design of Experiments (DOE) is a systematic and rigorous approach to engineering problemsolving. It is a structured, organized method for determining the connection between the factors that affect a process and its output. DOE applies principles and techniques at the data collection stage of the analysis that ensures the generation of defensible, and supportable engineering conclusions. It can be carried out under the constraint of a minimal expenditure of resources (engineering runs, time, and money).

Benefits of DOE
DOE is typically applied to an experiment involving random variables. In this context it has many benefits versus a traditional “best fit” approach. DOE is based on statistics. Statistics are objective, efficient and revealing.
Process Variation
Process variation is reduced, process can be optimized, signaltonoise ratios of the controllable factors can be maximized through randomization, replication and blocking
Process variation is reduced, process can be optimized, signaltonoise ratios of the controllable factors can be maximized through randomization, replication and blocking

Simultaneous variable analysis
Multiple process variables and responses are studied simultaneously modeling determines the casual effect of factors on responses as well as interactions of factors and their effect on a response.
Point prediction
Saves time and money by predicting data points without the need to perform an experiment to get the data point.
Utilizes Analysis of Variance (ANOVA). ANOVA allows identification of significant model terms and assessment of model adequacy of the response surfaces by analyzing the models, residuals, summary statistics and the correlations between outputs. It is a test procedure which provides a statistically sound analysis of experimental data. The variance of the response is partitioned into source contributions from the chosen factors and their interactions as well as the random error.
Quantifies uncertainty
Provides a means of understanding the reasonable range for a response prediction at a given confidence level
Confirmation points
Points not used to build a model but used to prove that the model provides good estimates
Response Surface Methodology (RSM) is a superset of DOE with an emphasis on higher order modeling.
Multiple process variables and responses are studied simultaneously modeling determines the casual effect of factors on responses as well as interactions of factors and their effect on a response.
Point prediction
Saves time and money by predicting data points without the need to perform an experiment to get the data point.
Utilizes Analysis of Variance (ANOVA). ANOVA allows identification of significant model terms and assessment of model adequacy of the response surfaces by analyzing the models, residuals, summary statistics and the correlations between outputs. It is a test procedure which provides a statistically sound analysis of experimental data. The variance of the response is partitioned into source contributions from the chosen factors and their interactions as well as the random error.
Quantifies uncertainty
Provides a means of understanding the reasonable range for a response prediction at a given confidence level
Confirmation points
Points not used to build a model but used to prove that the model provides good estimates
Response Surface Methodology (RSM) is a superset of DOE with an emphasis on higher order modeling.