rncReg-class: Class '"rncReg"'

In netcoh: Statistical Modeling with Network Cohesion

Description

A generic class for regression objects with network cohesion.

Objects from the Class

Objects can be created by calls of the form new("rncReg", ...).

Slots

alpha:

The individual effects of the regression.

beta:

The fixed effects or covariate coefficients of the regression.

A:

The network adjacency matrix for which cohession is assumed.

lambda:

Parameter for cohesion penalty.

X:

Covariate matrix.

Y:

Response matrix.

dt:

The response data frame with the first column being the observed time and the second column being the event indicator.

gamma:

Regularization parameter for graph Laplacian.

cv:

Number of folds in cross-validation.

cv.loss:

Cross-validated prediciton loss. It is MSE for linear regression, binomial deviance for logistic regression and test partial loglikelihood for Cox's model (see reference paper).

cv.sd:

Standard deviation of cross-validation loss. It can be used for cross-validation by 1 sigma rule. It is more robust to noises.

model:

The specific regression model used.

Methods

No methods defined with class "rncReg" in the signature.

Author(s)

Tianxi Li, Elizaveta Levina, Ji Zhu
Maintainer: Tianxi Li [e-mail]

References

Tianxi Li, Elizaveta Levina and Ji Zhu. (2016) Regression with network cohesion, http://arxiv.org/pdf/1602.01192v1.pdf
Verweij, Pierre JM, and Hans C. Van Houwelingen. (1993) Cross-validation in survival analysis, Statistics in medicine 12, no. 24: 2305-2314.

See Also

rncreg

netcoh documentation built on May 2, 2019, 8:19 a.m.