Function Use Statistics and Faq more info on R Squared statistic: Difference between pages

From Eigenvector Research Documentation Wiki
(Difference between pages)
Jump to navigation Jump to search
imported>Jeremy
 
imported>Lyle
No edit summary
 
Line 1: Line 1:
Some versions of PLS_Toolbox and Solo contain a feature which allows you to contribute anonymous "Function Use" information to the Eigenvector Research developers team. This information is ONLY used to help us better understand which features are most used and, therefore, where our development effort is best spent in making your experience better.
===Issue:===


===Opt-In===
Can you give me more information on the R-Squared statistic?


This feature is completely "opt-in" meaning that it will '''NOT''' collect or send any information unless you explicitly tell it that you want to participate. Once you've been asked once, it will not ask you again (unless you clear all program settings, for example, if you uninstall and re-install from scratch.) But under no circumstances will it ever send use information unless you have explicitly told it you want to do so.
===Possible Solutions:===


===What Information Is '''Not''' Collected?===
R-Squared (R<sup>2</sup>) is an assessment of how well the model does the prediction (it is similar to RMSEC except that it doesn't show if there is a bias).


The information collected by this feature '''includes absolutely NO information about:''' your data, you, your computer, your company/affiliated organization, your location, your IP address, your Eigenvector Research account or license number, nor any other personally-identifiable information.
You can access the R<sup>2</sup> by right-clicking on a scores plot of predicted vs. measured. It is one of the items which show up in the information box ("Show on figure" puts it on the figure).  


===What Information '''Is''' Collected?===
Note: in other software, R<sup>2</sup> is for the MODELED data only. In PLS_Toolbox we calculate it for the DISPLAYED data. That means that if you show excluded data, or if you show predicted/test data with calibration data ("Show Cal with Test") the R<sup>2</sup> will be for what is shown and will be different from the calibration data. Turn off the "Show Cal with Test" checkbox on the Plot Controls window to view the R<sup>2</sup> for only the test data.


This feature counts the number of times you execute "high-level" functions in the software and combines this with the product name (e.g. "PLS_Toolbox", "Solo", "Solo+MIA") and version number, and whether the given product is running with an expiring "Demo" license code. This information is periodically sent to Eigenvector Research (e.g. every 30 minutes) along with a completely random "session" code which allows combining all the submissions from that given session of using the software. The session key changes randomly each time you start up the software and can only be used to assure that all your use information is correctly accumulated for that session.
R<sup>2</sup> is calculated as the square of the correlation coefficient between the X and Y axes plotted in the figure. If the only data shown is the estimation of the calibration Y data vs. the actual calibration Y data, this is nearly the same as the standard R<sup>2</sup> for a model as defined by, e.g. Martens and Naes.  


You have the '''OPTION''' to also submit reports with a random anonymous "user" code which will help us understand how individual users make user of the software. Even when this feature is enabled, your submissions will '''always''' be anonymous in that we can and will never connect any use information with a given physical end-user. This code is simply used to aggregate multiple sessions together with a given installation of the software.


===Example Report===
'''Still having problems? Please contact our helpdesk at [mailto:helpdesk@eigenvector.com helpdesk@eigenvector.com]'''


Below is an example of a report collected by one of the Eigenvector Research staff during a short period of time:
[[Category:FAQ]]
 
      user: ' '
    session: '7K11NUCBT27EUQAMF2LTFVJXY'
    product: 'PLS_Toolbox'
    version: '7.0.3'
    isdemo: 0
 
This information is followed by the actual "use" information:
 
          cumulative: 58
                pca: 6
                auto: 3
            normset: 1
      wlsbaselineset: 3
        wlsbaseline: 1
            baseline: 1
        poissonscale: 1
              flucut: 1
          evrimodel: 1
          evriscript: 1
            mdcheck: 8
          pcaengine: 3
      residuallimit: 2
              scale: 8
          plotscores: 2
      plotscores_pca: 2
    knnscoredistance: 4
        inheritimage: 1
          figbrowser: 2
            plotgui: 1
        classmarkers: 2
        peakfindgui: 2
    plotgui_toolbar: 2

Latest revision as of 13:23, 2 January 2019

Issue:

Can you give me more information on the R-Squared statistic?

Possible Solutions:

R-Squared (R2) is an assessment of how well the model does the prediction (it is similar to RMSEC except that it doesn't show if there is a bias).

You can access the R2 by right-clicking on a scores plot of predicted vs. measured. It is one of the items which show up in the information box ("Show on figure" puts it on the figure).

Note: in other software, R2 is for the MODELED data only. In PLS_Toolbox we calculate it for the DISPLAYED data. That means that if you show excluded data, or if you show predicted/test data with calibration data ("Show Cal with Test") the R2 will be for what is shown and will be different from the calibration data. Turn off the "Show Cal with Test" checkbox on the Plot Controls window to view the R2 for only the test data.

R2 is calculated as the square of the correlation coefficient between the X and Y axes plotted in the figure. If the only data shown is the estimation of the calibration Y data vs. the actual calibration Y data, this is nearly the same as the standard R2 for a model as defined by, e.g. Martens and Naes.


Still having problems? Please contact our helpdesk at helpdesk@eigenvector.com