estim_ncp

Estimate the number of components in PCA .

multivariate

Exploratory data analysis methods to summarize, visualize and describe datasets. The main principal component methods are available, those with the largest potential in terms of applications: principal component analysis (PCA) when variables are quantitative, correspondence analysis (CA) and multiple correspondence analysis (MCA) when variables are categorical, Multiple Factor Analysis when variables are structured in groups, etc. and hierarchical cluster analysis. F. Husson, S. Le and J. Pages (2017).

Francois Husson

FactoMineR

Multivariate Exploratory Data Analysis and Data Mining

estim_ncp function

<dl> <dt>X</dt>
<dd>a data frame with continuous variables</dd> <dt>ncp.min</dt>
<dd>minimum number of dimensions to interpret, by default 0</dd> <dt>ncp.max</dt>
<dd>maximum number of dimensions to interpret, by default NULL which corresponds to the number of columns minus 2</dd> <dt>scale</dt>
<dd>a boolean, if TRUE (value set by default) then data are scaled to unit variance</dd> <dt>method</dt>
<dd>method used to estimate the number of components, "GCV" for the generalized cross-validation approximation or "Smooth" for the smoothing method (by default "GCV")</dd></dl>

Arguments

Francois Husson <a href="/link/francois.husson%40institut-agro.fr?package=FactoMineR&version=2.9" data-mini-rdoc="FactoMineR::francois.husson@institut-agro.fr">francois.husson@institut-agro.fr</a>, Julie Josse<a href="/link/Julie.Josse%40agrocampus-ouest.fr?package=FactoMineR&version=2.9" data-mini-rdoc="FactoMineR::Julie.Josse@agrocampus-ouest.fr">Julie.Josse@agrocampus-ouest.fr</a>

Author

Estimate the number of components in Principal Component Analysis — estim_ncp

<dl>

 <dt>X</dt>
<dd>a data frame with continuous variables</dd>

 <dt>ncp.min</dt>
<dd>minimum number of dimensions to interpret, by default 0</dd>

 <dt>ncp.max</dt>
<dd>maximum number of dimensions to interpret, by default NULL which corresponds to the number of columns minus 2</dd>

 <dt>scale</dt>
<dd>a boolean, if TRUE (value set by default) then data are scaled to unit variance</dd>

 <dt>method</dt>
<dd>method used to estimate the number of components, "GCV" for the generalized cross-validation approximation or "Smooth" for the smoothing method (by default "GCV")</dd>

</dl>

Francois Husson <a href='mailto:francois.husson@institut-agro.fr'>francois.husson@institut-agro.fr</a>, Julie Josse<a href='mailto:Julie.Josse@agrocampus-ouest.fr'>Julie.Josse@agrocampus-ouest.fr</a>

estim_ncp: Estimate the number of components in Principal Component Analysis

Description

Usage

Value

Arguments

Author

References

See Also

Examples