Contains the results of a classical Principal Components Analysis

PcaClassic-class

Robust Location and Scatter Estimation and Robust
Multivariate Analysis with High Breakdown Point:
principal component analysis (Filzmoser and Todorov (2013), <doi:10.1016/j.ins.2012.10.017>),
linear and quadratic discriminant analysis (Todorov and Pires (2007)),
multivariate tests (Todorov and Filzmoser (2010) <doi:10.1016/j.csda.2009.08.015>),
outlier detection (Todorov et al. (2010) <doi:10.1007/s11634-010-0075-2>).
See also Todorov and Filzmoser (2009) <urn:isbn:978-3838108148>,
Todorov and Filzmoser (2010) <doi:10.18637/jss.v032.i03> and
Boudt et al. (2019) <doi:10.1007/s11222-019-09869-x>.

Valentin Todorov

rrcov

Scalable Robust Estimators with High Breakdown Point

PcaClassic-class function

Class "PcaClassic" - Principal Components Analysis — PcaClassic-class

Objects can be created by calls of the form <code>new("PcaClassic", ...)</code> but the 
 usual way of creating <code>PcaClassic</code> objects is a call to the function
 <code>PcaClassic</code> which serves as a constructor.

Objects from the Class

<dl>
 <dt><code>call</code>:</dt>
<dd>Object of class <code>"language"</code></dd>

 <dt><code>center</code>:</dt>
<dd>Object of class <code>"vector"</code> the center of the data</dd>

 <dt><code>scale</code>:</dt>
<dd>Object of class <code>"vector"</code> the scaling applied to each variable</dd>

 <dt><code>rank</code>:</dt>
<dd>Object of class <code>"numeric"</code> the rank of the data matrix</dd>

 <dt><code>loadings</code>:</dt>
<dd>Object of class <code>"matrix"</code> the matrix 
 of variable loadings (i.e., a matrix whose columns contain the eigenvectors)</dd>

 <dt><code>eigenvalues</code>:</dt>
<dd>Object of class <code>"vector"</code> the eigenvalues</dd>

 <dt><code>scores</code>:</dt>
<dd>Object of class <code>"matrix"</code> the scores - the value 
 of the projected on the space of the principal components data (the centred 
 (and scaled if requested) data multiplied 
 by the <code>loadings</code> matrix) is returned. Hence, <code>cov(scores)</code> 
 is the diagonal matrix <code>diag(eigenvalues)</code></dd>

 <dt><code>k</code>:</dt>
<dd>Object of class <code>"numeric"</code> number of (choosen) principal components</dd>

 <dt><code>sd</code>:</dt>
<dd>Object of class <code>"Uvector"</code> Score distances within the robust PCA subspace</dd>

 <dt><code>od</code>:</dt>
<dd>Object of class <code>"Uvector"</code> Orthogonal distances to the robust PCA subspace</dd>

 <dt><code>cutoff.sd</code>:</dt>
<dd>Object of class <code>"numeric"</code> Cutoff value for the score distances</dd>

 <dt><code>cutoff.od</code>:</dt>
<dd>Object of class <code>"numeric"</code> Cutoff values for the orthogonal distances</dd>

 <dt><code>flag</code>:</dt>
<dd>Object of class <code>"Uvector"</code> The observations whose score distance is larger 
 than cutoff.sd or whose orthogonal distance is larger than cutoff.od can be considered 
 as outliers and receive a flag equal to zero.
 The regular observations receive a flag 1</dd>

 <dt><code>n.obs</code>:</dt>
<dd>Object of class <code>"numeric"</code> the number of observations</dd>

 <dt><code>eig0</code>:</dt>
<dd>Object of class <code>"vector"</code> all eigenvalues</dd>

 <dt><code>totvar0</code>:</dt>
<dd>Object of class <code>"numeric"</code> the total variance explained (<code>=sum(eig0)</code>)</dd>

 
</dl>

Slots

Class <code>"Pca"</code>, directly.

Extends

<dl>
 <dt>getQuan</dt>
<dd><code>signature(obj = "PcaClassic")</code>: returns the number of 
 observations used in the computation, i.e. n.obs</dd>

 
</dl>

Methods

Valentin Todorov <a href='mailto:valentin.todorov@chello.at'>valentin.todorov@chello.at</a>

PcaClassic-class: Class "PcaClassic" - Principal Components Analysis

Description

Arguments

References

See Also

Examples