Doe10 factorial2k blocking
Download as PPT, PDF1 like978 views
This document discusses blocking and confounding in 2k factorial designs. It explains that blocking is used to reduce noise in experiments, and confounding involves assigning treatments to experimental units in a way that balances out systematic errors. The document provides examples of chemical yield, filtration rate, and etching process experiments to illustrate 2k factorial designs with different numbers of blocks and how confounding works. It demonstrates randomization techniques and shows experimental design layouts. The overall purpose is to explain how to design experiments with blocks and use confounding to make comparisons between treatment combinations more reliable.
Doe10 factorial2k blocking
- 1. Blocking and Confounding in the 2k Factorial Design ARIF RAHMAN 1
- 2. Experiments Hypothesis/ Conjecture Design of Experiment Conduct Experiment Analysis of Data Discussion & Conclusion Refine the Model 2
- 3. Elements of Design of Experiments 1. Conjecture or hypothesis 2. Response variable 3. Factors, levels and ranges 4. Treatments of factors 5. Blockings 6. Tools and methods for experiments and measurements 7. Effect models (independent or interaction factors) 8. Replication, randomization and local factor 3
- 4. P Diagram Signal Factors (m) Noise Factors (x) Control Factors (z) Scaling Factors (r) Response Variables (y) F(x,m,z,r) 4 Inputs Controllable Factors (x) Uncontrollable Factors (z) Output (y) F(x,z)
- 7. an Example: Chemical Yield Experiment 7
- 8. an Example: Chemical Yield Experiment 8
- 9. Confounding the 2k Factorial Design in Two Blocks 9
- 10. Confounding the 2k Factorial Design in Two Blocks 10
- 11. Confounding the 2k Factorial Design in Two Blocks 11
- 12. Confounding the 2k Factorial Design in Two Blocks 12
- 13. Confounding the 2k Factorial Design in Two Blocks 13
- 14. Confounding the 2k Factorial Design in Two Blocks 14
- 15. Confounding the 2k Factorial Design in Two Blocks 15
- 16. Confounding the 2k Factorial Design in Two Blocks 16
- 17. Confounding the 2k Factorial Design in Two Blocks 17
- 18. Confounding the 2k Factorial Design in Two Blocks 18 Randomization between blocks Replicate Block Random 1 1 2047 1 2 5589 2 1 3255 2 2 7641 3 1 6859 3 2 3455 4 1 4328 4 2 1391
- 19. Confounding the 2k Factorial Design in Two Blocks 19 Randomization within blocks Repl-Block Test Random 4.2 abc 2997 4.2 a 8220 4.2 b 3507 4.2 c 1522 : : : 2.2 abc 9450 2.2 a 5147 2.2 b 2085 2.2 c 4735
- 20. Confounding the 2k Factorial Design in Two Blocks 20
- 21. an Example: Filtration Rate Experiment 21
- 22. an Example: Filtration Rate Experiment 22
- 23. an Example: Filtration Rate Experiment 23
- 24. an Example: Filtration Rate Experiment 24
- 25. an Example: Filtration Rate Experiment 25
- 26. an Example: Filtration Rate Experiment 26
- 27. an Example: Filtration Rate Experiment 27
- 28. an Example: Filtration Rate Experiment 28
- 29. Confounding the 2k Factorial Design in Four Blocks 29
- 30. Confounding the 2k Factorial Design in Four Blocks 30
- 31. Confounding the 2k Factorial Design in Four Blocks 31
- 32. Confounding the 2k Factorial Design in Four Blocks 32
- 33. Confounding the 2k Factorial Design in 2p Blocks 33
- 34. Confounding the 2k Factorial Design in 2p Blocks 34
- 35. Confounding the 2k Factorial Design in 2p Blocks 35
- 36. Confounding the 2k Factorial Design in 2p Blocks 36
- 40. an Example: Etching Process Experiment 40
- 41. an Example: Etching Process Experiment 41
- 42. an Example: Etching Process Experiment 42
- 43. 43 That’s all ... Any Questions ???