MATLAB File Help: prtRvMvn
prtRvMvn
  prtRvMvn  Multivariate normal random variable
 
    RV = prtRvMvn creates a prtRvMvn object with empty mean and
    covariance matrices. The mean and covariance matrices must be set
    either directly, or by calling the MLE method.
 
    RV = prtRvMvn('covarianceStructure', VALUE) enforces a covariance
    structure, which may be either 'full', 'spherical', or 'diagonal'.
    Setting this property to 'spherical' or 'diagonal' will enforce
    this structure onto the existing covariance matrix, or one
    estimated by calling the MLE method.
 
    RV = prtRvMvn(PROPERTY1, VALUE1,...) creates a prtRvMv object RV
    with properties as specified by PROPERTY/VALUE pairs.
 
    A prtRvMvn object inherits all properties from the prtRv class. In
    addition, it has the following properties:
 
    covarianceStructure - A string specifying the structure of the
                          covariance matrix to estimate or enforce. 
                          Valid values are 'full','spherical', or 
                          'diagonal'
    mu                  - The mean of the distribution, which is
                          a 1 x nDimensions vector.
    sigma               - The covariance matrix of the distribution,
                          which is a nDimensions x nDimensions 
                          matrix.
    
   A prtRvMvn object inherits all methods from the prtRv class. The MLE
   method can be used to estimate the distribution parameters from
   data.
 
   Example:
 
   dataSet    = prtDataGenUnimodal;   % Load a dataset consisting of 2
                                      % classes
   % Extract one of the classes from the dataSet
   dataSetOneClass = prtDataSetClass(dataSet.getObservationsByClass(1));
 
   RV = prtRvMvn;                       % Create a prtRvMvn object
   RV = RV.mle(dataSetOneClass.getX);   % Compute the maximum
                                        % likelihood estimate from the
                                        % data
   RV.plotPdf                           % Plot the pdf
 
   RVspec = prtRvMvn;                   % Create another prtRvMvn
                                        % object
   RVspec.mu = [1 2];                   % Specify the mean
   RVspec.sigma = [2 -1; -1 2]          % Specify the covariance
   figure;
   RVspec.plotPdf                       % Plot the pdf
   sample = RVspec.draw(1)              % Draw 1 random sample from the
                                        % Distribution
See also
Class Details
Superclasses prtRv, prtRvMemebershipModel
Sealed false
Construct on load false
Constructor Summary
prtRvMvn Multivariate normal random variable 
Property Summary
covarianceStructure The covariance structure 
dataSet The training prtDataSet, only stored if verboseStorage is true.  
dataSetSummary Structure that summarizes prtDataSet. 
isCrossValidateValid  
isSupervised  
isTrained Indicates if prtAction object has been trained. 
mu The mean vector 
name  
nameAbbreviation  
plotOptions  
showProgressBar  
sigma The covariance matrix 
userData User specified data 
verboseStorage Specifies whether or not to store the training prtDataset. 
Method Summary
  cdf Output the cdf of the random variable evaluated at the points specified 
  crossValidate Cross validate prtAction using prtDataSet and cross validation keys. 
  draw Draw random samples from the distribution described by the prtRv object 
  get get the object properties 
protected   getNumDimensions  
  initializeMixtureMembership  
  kfolds Perform K-folds cross-validation of prtAction 
  logPdf Output the log pdf of the random variable evaluated at the points specified 
  mle Compute the maximum likelihood estimate  
  optimize Optimize action parameter by exhaustive function maximization. 
  pdf Output the pdf of the random variable evaluated at the points specified 
  plotCdf Plots the CDF of the prtRv 
  plotLogPdf Plot the pdf of the prtRv 
  plotPdf Plot the pdf of the prtRv 
  run Run a prtAction object on a prtDataSet object. 
  set set the object properties 
  train Train a prtAction object using training a prtDataSet object.