Description Usage Arguments Value
View source: R/dual.ridge.lm.R
Implementation of the dual analytical solution for a linear regression model with a Ridge penalty term.
1 2 3 4 5 6 7 8 9 10 11 |
formula |
an object of class |
data |
an optional data frame, list or environment (or object coercible
by |
lambda |
penalty term scaling hyperparameter. |
intercept |
optional boolean indicating whether to fit an intercept. If
|
standardize |
optional boolean indicating whether to return results for
standardized data. If |
kernel |
optional kernel to use in the ridge regression model. By default the linear kernel with constant zero is used, that is, no kernel transformation is applied. See the details section for more details on available kernel transformations. |
const |
optional constant parameter for the kernel transformation.
Default is |
degree |
optional degree parameter in the kernel transformation. Default
is |
scale |
optional scale parameter in the kernel transformation. Default
is |
dual.ridge.lm
returns an object of class
mlkit.dual.ridge.fit
. An object of class mlkit.dual.ridge.fit
is a list containing at least the following components:
coefficients |
a named vector of optimal coefficients. |
alpha |
L1-weight hyperparameter in elastic net penalty term. |
lambda |
penalty term scaling hyperparameter. |
r2 |
coefficient of determination for optimal coefficients. |
x |
matrix containing the explanatory variables used in estimation. |
ker.mat |
kernel matrix used in estimation. |
kernel |
kernel transformation. |
const |
constant parameter in the kernel transformation. |
degree |
degree parameter in the kernel transformation. |
scale |
scale parameter in the kernel transformation. |
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.