optionsFCnet.Rd
Set or get options for FCnet
optionsFCnet(...)
family | Defaults to "gaussian." Experimental support for "binomial" on the way. |
---|---|
cv.type.measure | The measure to minimize in crossvalidation inner loops. The deafult is the mean squared error. |
cv.criterion | Whether crossvalidated models are chosen on the basis of their error or - relevant when different number of components are compared - AIC or BIC criteria. |
intercept | whether to fit (TRUE) or not (FALSE) an intercept to the model. Useful if y is not scaled and centered. |
standardize | Whether x must be standardized internally to |
whichLambda | During crossvalidation, either selects "lambda.min" - which chooses the value of lambda which best minimizes the mean crossvalidation error - or "lambda.1se" - which "which gives the most regularized model such that error is within one standard error of the minimum". The latter would be preferable for stability. |
thresh | Threshold for glmnet to stop converging to the solution. This parameter can be adapted (e.g. for speed / accuracy tradeoff). |
consensus_function | which function is used to create consensus between coefficients from different models. |
nested | Whether crossvalidation is to be performed in a nested fashion. |
colorPaletteDefault | The default color palette for plotting matrices (a vector of colors). |
colorNuances | Number of nuances along the provided colorPalette. |