Subscribe Bookmark
KarenC

Super User

Joined:

Feb 10, 2013

Design of experiment: Analysis by model visualization

Last week, I described model visualization – which is simply applying data visualization to models – and explained why I find it useful.

Designed experiments, especially small DOEs, are a perfect place to practice model visualization. Another term for this could be “analysis by Graph Builder.”

I am not suggesting that you don’t build numerical models and look at parameter estimates, p-values and residuals. However, I am saying, “Plot the data.” I often will plot the data, build the model, revisit the plots and revisit the models. That is, graphics are part of my model-building process.

For example, I was sent the results of a four-factor fractional factorial design by a client. In Graph Builder, I plotted the four main effects and found that not only did factor X_4 have a strong effect, but I could also see something fun at the high level of  X_4. The two groupings of data immediately suggest an interaction.

DOE_Model_Visualization_JMP

With the interactivity of JMP, you can highlight the data and quickly figure out that the groupings at the high level of X_4 are most likely due to the level of X_2.

DOE_Model_Visualization_JMP_2

So it took four factors, eight runs, data collection and measurements, followed by a quick analysis in Graph Builder to show that the outcome appears to be driven by X_4, with the impact of X_4 dependent on X_2.

This Graph Builder analysis was all that was needed for this small designed experiment. To me, this is the beauty of DOE – and model visualization.

 

2 Comments
Community Member

Melissa wrote:

Thanks for sharing this example. Can't disagree: plotting the data is the first crucial thing to do before any modeling.

I tend to disagree when you said : so it only took 4 factors, eight runs... For me one crucial step that I guess is implicit here is the brainstorming on the Factors (which + levels...), the outcome of interest... These discussions are for me the most important before building any DOE and it's an interesting stage for us!!

Best

Mélissa

Community Member

Karen wrote:

Melissa,

Agreed, I was over simplistic my statement. Once the factors and levels were determined and the design was constructed, then the rest fell into place. The factor and level selections is a most crucial step and as you indicated an interesting stage in which discussion is good.

Karen