Algorithmic constants and parameters for running <code>vgam</code>
 are set using this function.

vgam.control

An implementation of about 6 major classes of
statistical regression models. The central algorithm is
Fisher scoring and iterative reweighted least squares.
At the heart of this package are the vector generalized linear
and additive model (VGLM/VGAM) classes. VGLMs can be loosely
thought of as multivariate GLMs. VGAMs are data-driven
VGLMs that use smoothing. The book "Vector Generalized
Linear and Additive Models: With an Implementation in R"
(Yee, 2015) <DOI:10.1007/978-1-4939-2818-7> gives details of
the statistical framework and the package. Currently only
fixed-effects models are implemented. Many (100+) models and
distributions are estimated by maximum likelihood estimation
(MLE) or penalized MLE. The other classes are RR-VGLMs
(reduced-rank VGLMs), quadratic RR-VGLMs, doubly constrained
RR-VGLMs, quadratic RR-VGLMs, reduced-rank VGAMs,
RCIMs (row-column interaction models)---these classes perform
constrained and unconstrained quadratic ordination (CQO/UQO)
models in ecology, as well as constrained additive ordination
(CAO). Hauck-Donner effect detection is implemented.
Note that these functions are subject to change;
see the NEWS and ChangeLog files for latest changes.

Thomas Yee

VGAM

Vector Generalized Linear and Additive Models

Cleve Moler

vgam.control function

Control Function for vgam() — vgam.control

<dl>



 <dt>all.knots</dt>
<dd>logical indicating if all distinct points of
 the smoothing variables are to be used as knots.
 By default, <code>all.knots=TRUE</code> for
 \(n \leq 40\), and
 for \(n &gt; 40\),
 the number of knots is approximately
 \(40 + (n-40)^{0.25}\).
 This increases very slowly with \(n\)
 so that the number of knots is approximately between 50 and 60
 for large \(n\).
</dd>

 <dt>bf.epsilon</dt>
<dd>tolerance used by the modified vector
 backfitting algorithm for testing convergence.
 Must be a positive number.
</dd>

 <dt>bf.maxit</dt>
<dd>maximum number of iterations allowed in
 the modified vector
 backfitting algorithm. Must be a positive integer.
</dd>

 <dt>checkwz</dt>
<dd>logical indicating whether the diagonal elements of
 the working weight matrices should be checked
 whether they are
 sufficiently positive, i.e., greater
 than <code>wzepsilon</code>. If not,
 any values less than <code>wzepsilon</code> are
 replaced with this value.
</dd>

 <dt>Check.rank, Check.cm.rank</dt>
<dd>See <code>vglm.control</code>.

</dd>


 <dt>criterion</dt>
<dd>character variable describing what criterion is to
 be used to test for convergence.
 The possibilities are listed
 in <code>.min.criterion.VGAM</code>, but
 most family functions only implement a few of these.
</dd>

 <dt>epsilon</dt>
<dd>positive convergence tolerance epsilon. Roughly
 speaking, the
 Newton-Raphson/Fisher-scoring/local-scoring iterations
 are assumed to have
 converged when two successive <code>criterion</code>
 values are within
 <code>epsilon</code> of each other.
</dd>

 <dt>maxit</dt>
<dd>maximum number of
 Newton-Raphson/Fisher-scoring/local-scoring
 iterations allowed.
</dd>

 <dt>Maxit.outer</dt>
<dd>maximum number of
 outer iterations allowed when there are
 <code>sm.os</code> or
 <code>sm.ps</code> terms.
 See <code>vgam</code> for a little information about
 the default outer iteration.
 Note that one can use performance iteration
 by setting <code>Maxit.outer = 1</code>; then the
 smoothing parameters will be automatically chosen at each
 IRLS iteration (some specific programming
 allows this).


Note that <code><a href='https://rdrr.io/pkg/mgcv/man/gam.html'>gam</a></code> uses
 outer iteration by default. However, 
 <code><a href='https://rdrr.io/pkg/mgcv/man/magic.html'>magic</a></code> is only
 invoked for the Gaussian family, so
 the results of <code><a href='https://rdrr.io/pkg/mgcv/man/gam.html'>gam</a></code>
 may differ substantially from
 <code>sm.os</code> and <code>sm.ps</code>
 in general.





</dd>

 <dt>na.action</dt>
<dd>how to handle missing values.
 Unlike the SPLUS <code>gam</code> function,
 <code>vgam</code> cannot handle
 <code>NA</code>s when smoothing.
</dd>

 <dt>nk</dt>
<dd>vector of length \(d\) containing positive integers.
 where \(d\) be the number of <code>s</code> terms
 in the formula.
 Recycling is used if necessary.
 The \(i\)th value is the number of
 B-spline coefficients to be
 estimated for each component function of the \(i\)th
 <code>s()</code> term.
 <code>nk</code> differs from the number of knots by some constant.
 If specified, <code>nk</code> overrides the
 automatic knot selection procedure.

</dd>

 <dt>save.weights</dt>
<dd>logical indicating whether the <code>weights</code> slot
 of a <code>"vglm"</code> object will be saved on the object.
 If not, it will be reconstructed when needed,
 e.g., <code>summary</code>.
</dd>

 <dt>se.fit</dt>
<dd>logical indicating whether approximate
 pointwise standard errors are to be saved on the object.
 If <code>TRUE</code>, then these can be plotted
 with <code>plot(..., se = TRUE)</code>.

</dd>

 <dt>trace</dt>
<dd>logical indicating if output should be produced
 for each iteration.
</dd>

 <dt>wzepsilon</dt>
<dd>Small positive number used to test whether the diagonals
 of the working weight matrices are sufficiently positive.

</dd>


</dl>










<dl>


 <dt>noWarning</dt>
<dd>Same as <code>vglm.control</code>.


</dd>

 <dt>xij</dt>
<dd>Same as <code>vglm.control</code>.


</dd>

 <dt>gamma.arg</dt>
<dd>Numeric; same as <code>gamma</code> in <code><a href='https://rdrr.io/pkg/mgcv/man/magic.html'>magic</a></code>.
 Inflation factor for optimizing the UBRE/GCV criterion.
 If given, a suggested value is 1.4 to help avoid overfitting,
 based on the work of Gu and co-workers
 (values between 1.2 and 1.4 appeared reasonable,
 based on simulations).
 A warning may be given if the value is deemed out-of-range.


</dd>

 <dt>...</dt>
<dd>other parameters that may be picked up from control
 functions that are specific to the VGAM family function.

</dd>

</dl>

vgam.control: Control Function for vgam()

Description

Usage

Arguments

Value

Details

References

See Also

Examples