Exploratory Analysis and Release Notes Model Exporter Version 3 2: Difference between pages

From Eigenvector Research Documentation Wiki
(Difference between pages)
Jump to navigation Jump to search
imported>Jeremy
No edit summary
 
imported>Jeremy
(Created page with "Version 3.2 of Model_Exporter was released in June, 2015. For general product information, see Model_Exporter_User_Guide. ==NEW FEATURES / FIXES== * Add support for non-...")
 
Line 1: Line 1:
Exploratory analysis methods examine data for trends, correlations, or other relationships. Sometimes, models are created which can later identify when new data does not follow the same trend as previous data (see, for example, using [[pca|principal components analysis]] in multivariate statistical process control, see: [[Process Control and Statistics]]) or can be used to predict an amount of material or property (which is also discussed in [[Quantitative_Regression_Analysis|Quantitative Regression Analysis]].) Often, however, these methods are used simply to learn more about the data.
Version 3.2 of Model_Exporter was released in June, 2015. For general product information, see [[Model_Exporter_User_Guide]].


==Top-Level Exploratory Analysis Functions==
==NEW FEATURES / FIXES==
These functions provide high-level analysis of data. Most have various options and output model structures.


:[[analysis]] - Graphical user interface for data analysis.
* Add support for non-negative least squares CLS models IF outputting to m-file format (requires function be enabled as sub-functions are added to accomplish the NNLS calculation)
:[[pca]] - Principal components analysis.
* Add support for approximate nearest neighbor distance via distancemetric option. This is an approximation of the NN distance, but is NOT exact.
:[[mcr]] - Multivariate curve resolution with constraints.
* Add support for application of most preprocessing methods to MATRICES
:[[purity]] - Self-modeling mixture analysis method based on purity of variables or spectra.
** Allows use of PLS, PCR, PCA, CLS, and PLSDA on x-block of MATRICES (not just vectors) with basically all supported preprocessing methods
:[[cluster]] - Cluster analysis with dendrograms using various algorithms.
* Add basic support for arithmetic on X-block (only - undo on y-block not supported)
:[[corrspec]] - Correlation spectroscopy maps.
* Change "prob" to "probs" in SVMDA so it matches PLSDA outputs
:[[crossval]] - Cross-validation for decomposition and linear regression.
* Fix bug where placeholder variables were not removed from data if SavGol preprocessing was the one and only preprocessing method
:See Also [[Multiway Exploratory Analysis]]
* Fix bug which would lead to indexing error in SavGol preprocessing if variables at the END of the spectrum are excluded
 
==Evolving and Windowed Factor Analysis==
These function provide moving and "evolving" (growing) windowed analysis of data.
:[[evolvfa]] - Evolving factor analysis (forward and reverse).
:[[ewfa]] - Evolving window factor analysis.
:[[wtfa]] - Window target factor analysis.
 
==Other Exploratory Tools==
These are data-exploration tools, some of which provide interfaces to analyze the data or other medium-level analysis functionality.
 
:[[coda_dw]] - Calculates values for the Durbin_Watson criterion of columns of data set.
:[[coda_dw_interactive]] - Interactive version of CODA_DW.
:[[comparelcms_sim_interactive]] - Interactive interface for COMPARELCMS.
:[[estimatefactors]] - Estimate number of significant factors in multivariate data.
:[[manrotate]] - Graphical interface to manually rotate model loadings.
:[[mlpca]] - Maximum likelihood principal components analysis.
:[[trendtool]] - Univariate trend analysis tool.
 
==Application of Models to New Data==
In most cases, the function used to create a model (e.g. PCA, PLS, etc) is also used to make a prediction with the created model. See the function used for more information on this. In addition, these utilities may be of use for certain applications.
 
:[[modelselector]] - Create or apply a model selector model.
:[[compressmodel]] - Remove references to unused variables from a model.
:[[matchvars]] - Align variables of a dataset to allow prediction with a model.
:[[pcapro]] - Projects new data on old principal components model.


==Model Analysis and Calculation Utilities==
===Model Interpreter===
Low-level engine and calculation functions.


:[[qconcalc]] - Calculate Q residuals contributions for predictions on a model.
* Allow input of matrix instead of just vectors (some methods support applying to matrix)
:[[residuallimit]] - Estimates confidence limits for sum squared residuals.
* Force numeric conversion to be done expecting period as decimal separator (resolves problems interpreting models on systems set to other numeric formats like in France)
:[[reviewmodel]] - Examines a standard model structure for typical problems.
* Move math steps into new MEMath object (simplifies code - exposes mathematical operations to caller)
:[[tconcalc]] - Calculate Hotellings T2 contributions for predictions on a model.
:[[tsqlim]] - Confidence limits for Hotelling's T^2.
:[[varcap]] - Variance captured for each variable in PCA model.
:[[varimax]] - Orthogonal rotation of loadings.
 
 
:[[als]] - Alternating Least Squares computational engine.
:[[datahat]] - Calculates the model estimate and residuals of the data.
:[[dispmat]] - Calculates the dispersion matrix of two spectral data sets.
:[[pcaengine]] - Principal Components Analysis computational engine.
:[[tsqmtx]] - Calculates matrix for T^2 contributions for PCA.
:[[comparelcms_simengine]] - Calculational Engine for comparelcms.
 
==Plotting Utilities==
:[[modlrder]] - Displays model info for standard model structures.
:[[plotloads]] - Extract and display loadings information from a model structure.
:[[plotscores]] - Extract and display score information from a model.
:[[ploteigen]] - Builds dataset object of eigenvalues/RMSECV information.
:[[ssqtable]] - Displays variance captured table for model.
(Sub topic of [[Qualitative_Exploratory_Analysis_and_Classification|Qualitative_Exploratory_Analysis_and_Classification]])

Revision as of 15:49, 15 June 2015

Version 3.2 of Model_Exporter was released in June, 2015. For general product information, see Model_Exporter_User_Guide.

NEW FEATURES / FIXES

  • Add support for non-negative least squares CLS models IF outputting to m-file format (requires function be enabled as sub-functions are added to accomplish the NNLS calculation)
  • Add support for approximate nearest neighbor distance via distancemetric option. This is an approximation of the NN distance, but is NOT exact.
  • Add support for application of most preprocessing methods to MATRICES
    • Allows use of PLS, PCR, PCA, CLS, and PLSDA on x-block of MATRICES (not just vectors) with basically all supported preprocessing methods
  • Add basic support for arithmetic on X-block (only - undo on y-block not supported)
  • Change "prob" to "probs" in SVMDA so it matches PLSDA outputs
  • Fix bug where placeholder variables were not removed from data if SavGol preprocessing was the one and only preprocessing method
  • Fix bug which would lead to indexing error in SavGol preprocessing if variables at the END of the spectrum are excluded


Model Interpreter

  • Allow input of matrix instead of just vectors (some methods support applying to matrix)
  • Force numeric conversion to be done expecting period as decimal separator (resolves problems interpreting models on systems set to other numeric formats like in France)
  • Move math steps into new MEMath object (simplifies code - exposes mathematical operations to caller)