Dear all;
I have 4 factors to design my experiments. 3 of the factors are numerical but one is nominal.
for nominal factor I have 3 type as: A, B, C. the levels of A, B & C do not match each other.
I mean for each of them I have different levels of particle size as below:
For A - FIVE levels of particle size (F 320, F 400, F600, F800 & F 1000)
For B - FOUR levels of particle size (F 360, F 600, F800 & F 1000)
For C - SIX levels of particle size (F 120, F 360, F 400, F800, F 1000 & F 1200)
(The units of particle sizes are in FEPA grit and not important in the question)
briefly I have one factor (hardener factor) with 3 type (A, B & C) which every type has different number of levels that doesnt match each other. I need to design my experiments with these all.
could you please let me know what do you prefer me to do for designing?
Designing an experiment is usually associated with a reduction in the number of experiments compared to the complete experiment, with the least loss of information obtained. There is nothing to plan here in a such way.
Motashakkeram Mina ;
Just I think I mixed up a bit with your answer! if I assume A, B & C as my factors (like the attached figure) then the program would propose me (for example) choose one level of A with one level of B & C! I can't mix them with each other.
maybe I couldn't understand you well.
but I thought another solution please let me know your vision about that.
I can merge particle size factor into my nominal factor. then I would have 3 factors (one nominal and 2 numeric factor). the nominal factor would have 15 levels (C- F120, A-F320, B-F360,...) and the ratio and coating thickness factors kept unchanged.
Dependent variables must be continuous if you use ANOVA. But independent variables are nominal in ANOVA. To compare nominal dependent data, you use Chi Square
I do not change my mind and I admit. that this is not a case for which the principles of designing an experiment could be used. When planning an experiment, one need to define the factors (at least two), the range of their changes and the resulting variable depending on these factors. However, one can try to use statistical analysis here. But, repetitions are necessary.
Dear Mirosław Grzesik I try to reduce the number of experiments compared to the complete experiment. but in the time of designing I encountered a problem!
I think there is a misunderstanding because the question is complicated & maybe I couldn't explain that well. anyway I tried to merge two factors in one and now I have 3 factors instead of four factors and my first factor is in 18 levels (it is high because of merging two factors).
Thank you for your concern.
Dear Jabir Ismaeili, Apparently we have different points of view on the design of experiments. Of course, designing experiments is about reducing the number of tests performed in relation to the complete experiment. But what I can't imagine in your research is the result variable, also called the system response.
dear Mirosław Grzesik , for reducing the number of tests I need to introduce my factors to the software. But one of my factors had problem! that factor was the particle sizes in my access. I needed a way to solve introducing my factor to the software first.
Consider Plackett–Burman method:
https://en.wikipedia.org/wiki/Plackett%E2%80%93Burman_design https://www.itl.nist.gov/div898/handbook/pri/section3/pri335.htm
Dear Esmaeil Farmani Gheshlaghi & Dear Carlos Araújo Queiroz
Thank you for your consideration but my problem is about my factors and not the method. after solving this issues I will go with PB method.
My second factor (particle size) does not have equal levels for my materials. I mean for one material I have 4 particle size and for other 5 and the size of them also is not match! you can see the accessed particle sizes of each material in the attached image.
- Badges
- Science topic
- Similar topics
- Engineering
- Chemical Engineering