select

This functions give us the loadings from a "fanc" object for fixed value of gamma.

Computes the penalized maximum likelihood estimates of factor loadings and unique variances for various tuning parameters. The pathwise coordinate descent along with EM algorithm is used.  This package also includes a new graphical tool which outputs path diagram, goodness-of-fit indices and model selection criteria for each regularization parameter. The user can change the regularization parameter by manipulating scrollbars, which is helpful to find a suitable value of regularization parameter.

Kei Hirose

fanc

Penalized Likelihood Factor Analysis via Nonconvex Penalty

Michio Yamamoto

Haruhisa Nagata

select function

<dl> <dt>x</dt>
<dd>Fitted <code>"fanc"</code> model object.</dd> <dt>criterion</dt>
<dd>The criterion by which to select the tuning parameter rho. One of "AIC", "BIC", "CAIC", or "EBIC". Default is "BIC".</dd> <dt>gamma</dt>
<dd>The value of gamma.</dd> <dt>scores</dt>
<dd>Logical flag for outputting the factor scores. Defalut is FALSE.</dd> <dt>df.method</dt>
<dd>Two types of degrees of freedom are supported. If <code>"active"</code>, the degrees of freedom of are the number of nonzero parameters. If <code>"reparametrization"</code>, the degrees of freedom of the MC+ are reparametrized based on the degrees of freedom of the lasso.</dd></dl>

Arguments

Kei Hirose 
<a href="/link/mail%40keihirose.com?package=fanc&version=2.3.11" data-mini-rdoc="fanc::mail@keihirose.com">mail@keihirose.com</a>

Author

select from a "fanc" object for fixed value of gamma. — select

<dl>

 <dt>x</dt>
<dd>Fitted <code>"fanc"</code> model object.</dd>

 <dt>criterion</dt>
<dd>The criterion by which to select the tuning parameter rho. One of "AIC", "BIC", "CAIC", or "EBIC". Default is "BIC".</dd>

 <dt>gamma</dt>
<dd>The value of gamma.</dd>

 <dt>scores</dt>
<dd>Logical flag for outputting the factor scores. Defalut is FALSE.</dd>

 <dt>df.method</dt>
<dd>Two types of degrees of freedom are supported. If <code>"active"</code>, the degrees of freedom of are the number of nonzero parameters. If <code>"reparametrization"</code>, the degrees of freedom of the MC+ are reparametrized based on the degrees of freedom of the lasso.</dd>

</dl>

Kei Hirose 
<a href='mailto:mail@keihirose.com'>mail@keihirose.com</a>

select: select from a "fanc" object for fixed value of gamma.

Description

Usage

Value

Arguments

Author

References

See Also