Dear Veera,
The desirability function was originally developed by Harrington to simultaneously optimize the multiple responses and was later modified by Derringer and Suich
to improve its practicality. The desirability function approach is one of the most frequently used multi-response optimization techniques in practice. The desirability lies between 0 and 1 and it represents the closeness of a response to its ideal value.
If a response falls within the unacceptable intervals, the desirability is 0, and if a response falls within the ideal intervals or the response reaches its ideal value, the
desirability is 1.
R2 is a correlation coefficient.
E. Harrington, The desirability function, Industrial Quality Control, vol.
21, no. 10, 1965, pp. 494–498.
G. Derringer, R. Suich, Simultaneous optimization of several response
variables, Journal of Quality Technology, vol. 12, no. 4, 1980, pp. 214–
218.
http://waset.org/publications/14692/statistical-process-optimization-through-multi-response-surface-methodology
http://www.statease.com/pubs/RSM_for_peak_performance.pdf
Hoping this will be helpful,
Rafik
R sq, coefficient of determination is one of criteria to evaluate how close the data are to the fitted regression line. v need to chk 7 main criteria such as F value, p value, Rsq , SD, PRESS for confirming final model ....
Pls hv a look publication below for review all 7 criteria ....
In science field R sq more that 0.90 n d desirability more that 0.70 are acceptable ...
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4610787/
Multiple-Response Optimization means that more than one optimization criterion is considered at the same time. In order to do so, one Needs to convert the results of the different criteria into one scalar value.
The Approach works in two steps.
1. ramp functions from 0 to 1 will project the output variables to a value between 0 and 1, with 0 being very bad and 1 being ideal. Depending on the type of optimization, the ramp function will try to maximize, minimize or hit a target value (shaped like an inverted v).
2.Multiply the ramp values of the different criteria. The resultant value of the so called desirability function will be in the range of 0 and 1. 0 can be obtained if one or more of the single criteria are rated bad (resulting in a 0 of their ramp function). 1 will be obtained, if every criterion is perfect (rare case). The practical value will be lower than one, but the desirability function itself is typically smooth enough to be optimized with fairly simple algorithms.
Nice Approach. It does work in practice. However, you need to be a bit careful with the ramp functions. Do not expect too much and "overconstrain" the ramp functions. A reasonable / realistic definition will typically give you a decent result.
Hope that helped. Check my script (free download) for further info.
R2 shows the accuracy of the predicted value with the experimental value or the actual value. Desirability function when using numerical optimization method, gives you better understanding of the multi-response parameters during optimizing the cutting parameters. However, I will still advice you ready more to get the deep picture of it. Thanks
- Badges
- Science topic
- Similar topics
- Biological Science
- Biochemistry
- Biochemical Techniques
- Analytical Chemistry
- pH