Happy Christmas / Feliz Navidad

Desearos a todos los lectores de NIR-Quimiometría una ¡Feliz Navidad!.

y un Prospero y Feliz Año

 2013

I wish to all "NIR-Quimiometría" readers a Happy Christmas.

John Lennon says "Happy Christmas War is over"

Let´s hope to tell you some day:

"Happy Christmas Crisis is over"



Videos from Coursera’s four week course in R

Good information from the blog Revolution. Go to his post for more details.

Let´s keep these links in my label: "VIDEO: R Tutorials" to improve our R knowledge.

Computing for Data Analysis: Week 1

Computing for Data Analysis: Week 2

Computing for Data Analysis: Week 3

Computing for Data Analysis: Week 4

Laura Suttle : R tutorial videos

Laura Suttle : R tutorial videos

"R" : Identifying peaks

The function "identify"  from "R",  is very useful to check the spectrum for peaks or areas of interest. I use it here to see the wavelength with the highest variability in the Shootout-2012 Calibration Set.

This wavelength has a high variability due to the changes in concentration of the Active component in the mixture.

See the video to see how I use the function:



There are two books that I recomend to have to practice Chemometrics in R, you can find the links to get them from Amazon. Now that Christmas time is coming they can be nice presents to somebody. I will use them quite often as Bibliography in this blog.

We can use the identify option to check for the variables in X with the highest extreme loadings. In this case I use the element "rotation" generated by the object "prcomp".

Let´s use the same sample set as before: Shootout-2012 Calibration Set, and see the video:



As you can see the 216 value has the extreme value in both plots.

Why this bias? (Process)

I had a new set of samples for validation (process system), as I said in other posts, this is an exciting moment: Will the  calibration performs well?

My first reaction is to look to the plots (Lab vs Predicted). In this case I had this surprising plot:

There are some samples marked as x which have a bias. These are 12 samples (one for batch of flour production), taken randomly during the batch production. It is clear that something happened during the process, and that produced a bias, giving 3 points more of protein during that period.

I expected to have the same problem for moisture, ..., it was not so much, but all these samples has also a bias , being the residuals (Lab - Predicted) positive for all of them.

Same for ash, again these samples are apart from the others.

It is clear that something is happening with these samples. We have to take a look to the spectra.

To be continued.....

VIDEO: Working with ChemoSpec (HCA with the scores)