What prevents a matrix from being classified as spectra? When I right click on a data matrix which I imported from excel or imported from excel followed by transposing, the spectra option is grayed out and cannot be selected. I am importing spectral data so it would be really helpful to set it as such, but I can’t figure out what the problem is.

Answer To use the option to designate data as spectral, a column set needs to be defined (even if all the columns in the data are spectra. Once this is done, highlight the column set in the project navigator, right click, and toggle on "Spectra". With this setting, the loadings plots in the PCA overview will by default be shown as a line plot, and for PLS regression, the regression coefficients will be displayed in the PLS overview as a line plot. 0 votes

Hi all,I have an imported excel sheet I would like to reverse, that's to say exchange rows and colums. How can I deal with that ?Thank you

Answer Numeric data can be transposed in The Unscrambler X from the Tasks- Transform menu. From this menu select Transpose to complete this function on your data. -1 votes

How to use marked sample (in PCA score plot) to do PLS. Which need to connect with the original response data.Thanks.

Answer Dear Lily, Once samples have been marked in a plot, you can right click to "Create Range" from these samples. This row range can then be duplicated, by using "Insert->Duplicate Matrix". You can then add the reponse variables as a column to this range (if not already included) and do your PLS. 1 votes

Hi, I have a question about the PLS model. I have 20 samples with different concentration levels and each one is consisted of 500 points spectrum (wavelength). I build the PLS model by using one factor (PC1) and is good enough for the prediction. My question is: how to calculate back to confirm the original concentration levels. I used the PC1 with 500 variables times the original spectrum 500 points then add them up; the result is not the original concentration. Can you help me to figure how to process this issue. Thanks!

Answer In The Unscrambler X you can predict the values from a model by going to Tasks- Predict - Regression. The computation is based on the equation wherein the regression coefficients (B coefficients) for each variable, are multiplied by the values for new samples at each variable. In your case, you would multiply the spectral value at each of your 500 wavelengths by the regression coefficient for that wavelength, and sum them. 1 votes

Hi,I wanted to use your software to analyze my data using PCA in the same way I have seen it used in the paper "Evaluation of catalytic pyrolysis of cassava rhizome by principal component analysis" by Adisak Pattiya. My main problem is that I have a lot less samples than variables. I have spoken to a statastition and been informed that it would not make sense to perform PCA on my data in this case because of the number of degrees of freedom this would leave for the principle components. However the paper above also has far fewer samples than variables, could you let me know if your software can successfully apply PCA to data with 5 times less samples than variables?Thank you.

Answer Dear Angela, We use PCA quite frequently with large data sets with more variables than samples, as is the case with many instrumental analyses. Take for instance an FTIR spectrum that may have 1500 variables - but they are highly correlated so it is difficult to say how many degrees of freedom we have here. But we do want to analyze the data using multivariate analysis, and achieve a data reduction with PCA, hence extracting information from the latent variables (PCs). The Unscrambler is an ideal software tool for multivariate data analysis, and can eb applied to data sets with more variables than samples. 0 votes

1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 |