archive-com.com » COM » E » EIGENVECTOR.COM

Total: 295

Choose link from "Titles, links and description words view":

Or switch to "Titles and links view".
  • PLS_Toolbox FAQ
    Model Exporter DataSet Object DSO Floating Licenses Training Training Overview Eigenvector University EigenU Online Courses Resources Contact Us Search Site Search for FAQ Frequently Asked Questions Browse FAQ Browse Documentation Wiki Browse EigenGuide Videos Search for Keyword s Issue What are Relative Contributions Possible Solutions Relative Contributions are residuals or Hotelling s T 2 contribution reported as the difference between two samples or two groups of samples For more information

    Original URL path: http://eigenvector.com/faq/index.php?id=171 (2016-04-27)
    Open archived version from archive


  • PLS_Toolbox FAQ
    residuals are often reported in units which are sensitive to the total number of variables in the data and the number of components and particular preprocessing used for a model As a result comparison of values reported by different models or setting a standard alarm level for all models requires normalizing the statistics A common way to normalize the statistics is to divide by a confidence limit calculated from each

    Original URL path: http://eigenvector.com/faq/index.php?id=172 (2016-04-27)
    Open archived version from archive

  • PLS_Toolbox FAQ
    and RMSECV when cross validating PLSDA models Why do the cross validation curves look strange for PLSDA Possible Solutions Note this behavior has changed as of version 5 0 of PLS Toolbox and Solo RMSECV is now reported using the standard RMSECV equation see the documentation The misclassification rate discussed below is now reported separately With PLSDA cross validation reports the RMSEC and RMSECV in terms of fractional misclassification error rate That is an RMSECV of 0 05 indicates a 5 misclassification error rate This misclassification is based on the automatically determined threshold see FAQ on how this threshold is determined and the values predicted for each sample when it was in the test set left out of the model during cross validation The resulting RMSEC and RMSECV curves as a function of number of latent variables may be different from typical regression cross validation results This is because depending on the noise structure in the data the misclassification error rate may be less sensitive to number of components than a normal RMSECV might be You may see the RMSECV drop to zero and stay there as the number of components increases In these instances the latter latent variables do

    Original URL path: http://eigenvector.com/faq/index.php?id=63 (2016-04-27)
    Open archived version from archive

  • PLS_Toolbox FAQ
    than the JVM has allocated to it You may avoid this problem by configuring Matlab or Solo to grant more memory to Java Matlab and PLS Toolbox In Matlab 2009b and earlier versions you increase the allocated Java heap space by creating a file named java opts in your Program Files MATLAB R2009b bin win32 directory or win64 if you are using 64 bit Windows which contains the single line specifying how much memory to allocate to Java Xmx256m if you want to set 256 Mb for the Java heap This takes effect only after Matlab is restarted Take care to match the upper and lower case characters in that line and have no spaces between any characters If the error still occurs try increasing the memory allocation and repeat If you have specified a larger amount of memory than is available on your system then Matlab will not restart reduce the memory setting and continue Be aware that your system may not be able to supply enough memory for the Java task This java opts approach applies to other operating systems as well with the path of the java opts file being MATLABROOT bin ARCH directory MATLABROOT is the MATLAB root directory and ARCH is your system architecture See this Mathworks page for more details of this approach Matlab 2010a and later versions make it easier to specify the Java memory allocation by providing a graphical user interface This GUI is accessed from the Preferences File Preferences then under General Java Heap Memory See this Mathworks Technical Document for more details Solo For Solo and its various related products you increase the allocated Java heap space by creating a file named java opts in your Program Files EVRI Solo application bin win32 directory or win64 if you are using

    Original URL path: http://eigenvector.com/faq/index.php?id=136 (2016-04-27)
    Open archived version from archive

  • PLS_Toolbox FAQ
    MCR and PARAFAC models Possible Solutions MCR and PARAFAC both report the sum squared SSQ captured table with four statistics Fit X Fit Model Unique Fit X and Unique Fit Model All four of these statistics are all variants of variance captured although strictly speaking since the data is often not mean centered with this kind of analysis it is not variance but just sum squared signal The first two Fit X and Fit Model give the sum squared signal relative to the total signal in the data and to the total amount of signal captured in the model Fit X C i C X 100 Fit Model C i C model 100 where C i is the sum squared signal captured by the i th component C X is the sum squared signal in the entirety of the X matrix and C model is the sum squared signal captured by the model in total which is generally X because the model doesn t completely describe X Note that C model C 1 C 2 C 3 C i The second two statistics Unique Fit X and Unique Fit Model are the same as above except the components are first

    Original URL path: http://eigenvector.com/faq/index.php?id=133 (2016-04-27)
    Open archived version from archive

  • PLS_Toolbox FAQ
    Solo Predictor Model Exporter DataSet Object DSO Floating Licenses Training Training Overview Eigenvector University EigenU Online Courses Resources Contact Us Search Site Search for FAQ Frequently Asked Questions Browse FAQ Browse Documentation Wiki Browse EigenGuide Videos Search for Keyword s Issue What internal tests are used to select suggested number of PCs Possible Solutions The suggested number of components is calculated with the choosecomp m function For more information see

    Original URL path: http://eigenvector.com/faq/index.php?id=142 (2016-04-27)
    Open archived version from archive

  • PLS_Toolbox FAQ
    model where all y columns contribute to the loadings of the model This can sometimes improve performance of the model particularly when the signal in the different y columns is correlated but the noise is not A PLS1 model is a model built on a single y column and the model reflects only covariance between the X block and that single y column If you want separate PLS1 models for

    Original URL path: http://eigenvector.com/faq/index.php?id=93 (2016-04-27)
    Open archived version from archive

  • PLS_Toolbox FAQ
    to calculate scores T X P or to estimate data X T P These operations are invertible repeating them gives the same result because the loadings are the eigenvectors of X X When using Partial Least Squares PLS you get loadings P but also weights W because the decomposition is based on X Y The weights and loadings must be used together to calculate scores T X W pinv P

    Original URL path: http://eigenvector.com/faq/index.php?id=92 (2016-04-27)
    Open archived version from archive



  •