topic Re: Custom DOE do 3 replicates of each combination in Discussions

Custom DOE do 3 replicates of each combination

Agustin — Thu, 08 Jun 2023 20:58:59 GMT

I'm trying out the custom DOE tool and I'm not sure what the replicate runs option does.

I would like to specify that I want 20 combinations for example but I was to run each of those combinations 3 times, so we have 3 replicates of each combination and 60 runs in total.

What would be the best way to do this?

Thanks

Re: Custom DOE do 3 replicates of each combination

Byron_JMP — Fri, 05 Jun 2020 13:11:18 GMT

Replicates runs just makes one of your run conditions repeated.

It sounds like you plan to repeat your 20 runs 3 times?

In this case just add a column for each repeat. From here you have some decisions to make about repeated measures.

For example: I have 20 conditions I want to try and I'm running the experiment in a 96 well microtiter plate, so its easy to have repeats of the 20 conditions, plus I know there might be random position effects, so repeats are a good idea.

Are all 60 well independent runs? Well, no. They are all dependent on the one run. After I have all the data I would likely take the mean of the three repeats and use that as the response in my analysis of the experiment.

Re: Custom DOE do 3 replicates of each combination

statman — Fri, 05 Jun 2020 13:31:52 GMT

To add my thoughts to the discussion, repeats capture short-term effects not due to the treatments. This can be useful for being able to analyze measurement error or within treatment variation (due to the sources of variation changing between repeats). This data would need to be summarized to evaluate the treatments as repeats do not increase the degrees of freedom available.

Replication is a method to capture (and possibly assign) long-term variation due to "noise" so that you can:

1. determine if the results of the treatments from one replicate repeat for other replicates thereby increasing the inference space of the experiment

2. determine the size of the noise between replicates

3. increase the precision of detecting treatment effects while not compromising inference space

4. determine oil your results are robust to noise.