| T O P I C R E V I E W |
| Noname123 |
Posted - 10/27/2020 : 02:26:55 AM
On Analysis tab there's a correlation function which compute correlation between two signals. I need a correlation of two spectra. It gives out for each wn a correlation, but it exceeds 1 at some points. I am not clear how it computes the correlation. Does someone know? |
| 3 L A T E S T R E P L I E S (Newest First) |
| Szone1 |
Posted - 10/30/2020 : 11:43:01 AM
You might also try this:
https://www.originlab.com/fileExchange/details.aspx?fid=497 |
| Noname123 |
Posted - 10/27/2020 : 12:55:51 PM
I used correlation computation available at Analysis -> Signal Processing -> Correlation. And as input gave two separate columns that refer to intensities per each discrete wavelength. It gave warning that time data is not evenly spaced out so the average absolute increment will be selected. As an output it gave two columns: time and cor. Time is evenly spaced out vector that takes values from - 0.6 to 0.6. I don't know why.
What I'd like is correlation plot like this:
But I don't know how to do it. On both axis the plot has the same label, so I assumed that one set of intensities ( for each wavelength a corresponding intensity of signal ) are plotted against the other. But when I try to do it with two spectral data that I have, I get a nonsensical plot like this:
The intensity of signal is measured in relative absorbance units so the axis are scaled from 0 to 1. I have raw data of FTIR spectra, and I'd like to plot correlation plot between two spectra. I assume there is a way in origin to do this?
Each spectra is given as a column vector with corresponding intensities at each wavelength.
|
| 一击爆裂陈子豪 |
Posted - 10/27/2020 : 10:17:17 AM
Please provide more details. What tab are you using, which correlation type are you performing? Is your data in the correct form? Etc. |
