pen_fun

Calculate the penalty matrix for `mvmfd` objects.

Methods and tools for implementing regularized multivariate functional principal component analysis ('ReMFPCA') for multivariate functional data whose variables might be observed over different dimensional domains. 'ReMFPCA' is an object-oriented interface leveraging the extensibility and scalability of R6. It employs a parameter vector to control the smoothness of each functional variable. By incorporating smoothness constraints as penalty terms within a regularized optimization framework, 'ReMFPCA' generates smooth multivariate functional principal components, offering a concise and interpretable representation of the data. For detailed information on the methods and techniques used in 'ReMFPCA', please refer to Haghbin et al. (2023) <doi:10.48550/arXiv.2306.13980>.

Hossein Haghbin

ReMFPCA

Regularized Multivariate Functional Principal Component Analysis

Yue Zhao

Mehdi Maadooliat

pen_fun function

<dl><dt>data</dt>
<dd>an object of class `mvmfd`.</dd>
<dt>devorder</dt>
<dd>The order of the derivative.</dd>
<dt>type</dt>
<dd>The type of penalty. The types "coefpen" and "basispen" is supported.</dd></dl>

Arguments

Penalty Function — pen_fun

<dl>

<dt>data</dt>
<dd>an object of class `mvmfd`.</dd>


<dt>devorder</dt>
<dd>The order of the derivative.</dd>


<dt>type</dt>
<dd>The type of penalty. The types "coefpen" and "basispen" is supported.</dd>

</dl>

pen_fun: Penalty Function

Description

Usage

Value

Arguments