Description Usage Arguments Details Value Author(s) See Also
View source: R/summary.grpreg.R
Summarizes a fitted penalized regression model with 'grpreg
' class.
1 2 |
object |
A " |
lambda |
A regularization parameter at which to summarize. |
digits |
Number of digits past the decimal point to print out. The default is |
... |
Optional arguments passed to other methods. |
The default lambda
is the one at which we obtain the minimum loss
(i.e., negative log-likelihood value), if lambda
is not supplied.
A list with class "summary.grpreg
" containing the following components:
n |
Number of observations. |
p |
Number of screened predictors. |
penalty |
The penalty applied to the model. |
model |
The type of model. |
family |
The link function. |
criterion |
The screening criterion. |
lambda |
The default or specified regularization parameter. |
beta |
The estimates of coefficients at the specified |
iter |
The number of iterations at the specified |
df |
The estimates of effective number of model parameters at the specified
|
call |
The function call. |
Additional elements are contained for the case in which family = "gaussian"
:
r.squared |
The r.squared. |
snr |
The signal-to-noise ratio. |
scale |
The scale parameter estimate. |
and following elements for the case in which family = "poisson"
or "binomial"
:
logLik |
The negative log-likelihood values for the fitted model. |
aic |
Akaike's information criterion (AIC). |
bic |
Bayesian information criterion (BIC). |
aicc |
The AIC with a correction for finite sample sizes (AICC). |
pe |
The prediction error for |
Debin Qiu, Jeongyoun Ahn
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.