Plackett–Burman design is a well established and widely used statistical technique for selecting the most effective components with high significance levels for further optimization, ignoring interactions among variables (Plackett and Burman, 1946). The Plackett–Burman design was favorably used by many researchers (e.g. Haque et al., 2012.

• Plackett Burman Vs Fractional Factorial
• Minitab Plackett Burman

Plackett Burman Vs Fractional Factorial

DOE Pro XL

Minitab Plackett Burman

• DOE Software for Excel including Taguchi and Plackett-Burman templates. Download 30 day trial.
• Design-Expert software helps students set up and analyze two-level factorial, general factorial, fractional factorial,Plackett-Burman, and combined mixture/process designs, as well as response surface methods (RSM) analysis for up to 10 process factors or 24 mixture components.
• Plackett-Burman designs with 8 or 16 runs are not available in Create Factorial Design because each has a corresponding 2-level factorial design with an equal or better resolution. To open Create Factorial Design, go to Stat DOE Factorial Create Factorial Design.

Your Data is in Excel. Why isn’t Your Analysis?

doe designs to solve your problem

DOE Pro XL includes 2 Level Full and Fractional Factorial designs, 3 Level Full Factorial, Taguchi, Plackett-Burman, Central Composite, Box - Behnken, and Custom Designs. If you need help, use the Computer Aided design selection feature to pick the best design for your problem.

ANALYSIS Methods

Analyze your design using Multiple Regression, ANOVA, Multiple Plots, Marginal Means (Main effects) Plots, Residual Analysis, and more.

optimization and prediction

DOE Pro XL includes a powerful optimization engine capable of optimizing multiple responses at the same time. Prediction is designed into an Excel sheet making it exceptionally easy to use.

Excel Integration

DOE Pro XL integrates into Excel, streamlining your workflow and saving you time.

Introduction to Fractional Factorial Designs

Two-level designs are sufficient for evaluating many productionprocesses. Factor levels of ±1 can indicatecategorical factors, normalized factor extremes, or simply “up”and “down” from current factor settings. Experimentersevaluating process changes are interested primarilyin the factor directions that lead to process improvement.

For experiments with many factors, two-level full factorialdesigns can lead to large amounts of data. For example, a two-levelfull factorial design with 10 factors requires 2¹⁰ =1024 runs. Often, however, individual factors or their interactionshave no distinguishable effects on a response. This is especiallytrue of higher order interactions. As a result, a well-designed experimentcan use fewer runs for estimating model parameters.

Fractional factorial designs use a fraction of the runs requiredby full factorial designs. A subset of experimental treatments isselected based on an evaluation (or assumption) of which factors andinteractions have the most significant effects. Once this selectionis made, the experimental design must separate these effects. In particular,significant effects should not be confounded,that is, the measurement of one should not depend on the measurementof another.