Univariate vs. Multivariate Log Out | Topics | Search
Moderators | Register | Edit Profile

NIR Discussion Forum » Bruce Campbell's List » Chemometrics » Univariate vs. Multivariate « Previous Next »

Author Message
Top of pagePrevious messageNext messageBottom of page Link to this message

Tony Davies (Td)
Posted on Monday, August 08, 2005 - 6:13 am:   

Christina,

I have been writing about chemometrics in Spectroscopy Europe for many years. There might be something that would be helpful to you. You can download previous articles from:
www.spectroscopyeurope.com/td_col.html
Just to confuse you; the "Tony Davies" column is written (in alternate issues) by two Tony Davies's. I am AMC and write about chemometrics. AN writes about databases and related issues.

I think you are right to start from something they know. I also agree with Howard (!) It is best to avoid equations. Once you start, where do you stop? You would soon be needing to teach them matrix algebra!

Good luck!

Best wishes, Tony
Top of pagePrevious messageNext messageBottom of page Link to this message

Christina Timofeyenko (Ctimofeyenko)
Posted on Wednesday, August 03, 2005 - 10:18 am:   

Hello,
I have been doing some research in chemometrics and will be presenting my research to individuals who have little to no experience with chemometrics. Being a novice in the field myself I am looking to bridge the gap between univariate and multivariate calibration techniques. My hope is to keep people interested by first presenting something they know, traditional univariate techniques in spectroscopy i.e. Beer's law, and then describing how multivariate techniques are more applicable to NIR measurements. I would appreciate any personal input on the matter and references to websites, books, journal articles etc.
THANKS!
-Christina
Top of pagePrevious messageNext messageBottom of page Link to this message

hlmark
Posted on Wednesday, August 03, 2005 - 10:56 am:   

Christina - my best advice is: don't show any equations! Not even Beer's law, unless the audience is all spectroscopists who have used Beer's law previously. And even in that case, THAT'S ALL.

That still leaves spectra (real and/or synthetic), diagrams, graphs (even 3-D graphs if you can manage them), pictures and other visual representations of what you want to show.

It does make it harder, but chemometrics was never easy.

Howard

\o/
/_\

Add Your Message Here
Posting is currently disabled in this topic. Contact your discussion moderator for more information.