Showing results for 
Show  only  | Search instead for 
Did you mean: 
Choose Language Hide Translation Bar
Community Manager Community Manager
Spectral analysis in JMP 17 and JMP Pro 17

Spectral analysis is not new to JMP. There is just a renewed focus on analyzing spectral data. Spectral data is pervasive in chemistry and material science, and analyzing this data with statistically based software is growing rapidly. In fact, says JMP Systems Engineer Bill Worley (@Bill_Worley), there is a special name for this type of analysis: chemometrics. "Chemometrics is a set of multivariate analysis techniques that allows for preprocessing and modeling spectral data. The newest versions of JMP and JMP Pro are extremely good at performing chemometric analyses," Bill says. I asked him a few questions about spectral analysis.

What problems does this capability solve for our users?

Scientists and engineers, more specifically chemists and material scientists now have a one-stop solution for preprocessing (cleaning), investigating, and modeling their spectral data. JMP Pro 17 features preprocessing in the Functional Data Explorer platform, making it much easier clean your data and then analyze it with FDE. 

Can you give an example of how it might work for a JMP user?

Preprocessing of Near IR data using the newer tools in FDE. The bottom image shows the new Wavelet modeling functionality that is built into FDE.







What are the impacts this can make on users’ work and on organizations?

Preprocessing alone can help build more reliably predictive models. By having this capability built into the Functional Data Explorer platform, there is also a true time savings in analysis, visualization and understanding of spectral data. The FDE platform in itself is a unique capability that JMP offers among commercially available software to allow for analyzing “curve” data and spectral data fits the definition of curve data to a tee. Another important impact is that chemists and material scientists can use FDOE (functional design experiments) with spectral responses.

What do you think will be the user response to spectral analysis?

I've already heard that Egon-Eduard Gross from Symrise is very excited about the new spectral analysis capability built into to JMP.  We have discussed what is possible with him, and he is looking forward to jointly doing a future Discovery Summit presentation on this capability. Several other users have made comments on the spectral analysis blog posts that Jeremy Ash (@Anonymous) and I wrote with Mark Bailey’s (@Mark_Bailey) help expressing their delight at this.

Last Modified: Oct 20, 2022 7:44 PM