tune.glmnet.interval {c060}  R Documentation 
Wrapper function for glmnet
objects.
Description
Wrapper function for glmnet
objects used by epsgo
function.
This function is mainly used within the function epsgo
Usage
tune.glmnet.interval(parms, x, y,
weights,
offset = NULL,
lambda = NULL,
type.measure = c("mse", "deviance", "class", "auc", "mae"),
seed=12345,
nfolds = 10,
foldid=NULL,
grouped = TRUE,
type.min=c("lambda.min", "lambda.1se"),
family,
verbose=FALSE,
...)
Arguments
parms 
tuning parameter alpha for 
x , y 
x is a matrix where each row refers to a sample a each column refers to a gene; y is a factor which includes the class for each sample 
weights 
observation weights. Can be total counts if responses are proportion matrices. Default is 1 for each observation 
offset 
A vector of length nobs that is included in the linear predictor (a nobs x nc matrix for the "multinomial" family). Useful for the "poisson" family (e.g. log of exposure time), or for refining a model by starting at a current fit. Default is NULL. If supplied, then values must also be supplied to the predict function. 
lambda 
A user supplied lambda sequence. Typical usage is to have the program compute its own lambda sequence based on nlambda and lambda.min.ratio. Supplying a value of lambda overrides this. WARNING: use with care. Do not supply a single value for lambda (for predictions after CV use predict() instead). Supply instead a decreasing sequence of lambda values. glmnet relies on its warms starts for speed, and its often faster to fit a whole path than compute a single fit. 
type.measure 
loss to use for crossvalidation. Currently five options, not all available for all models. The default is type.measure="deviance", which uses squarederror for gaussian models (a.k.a type.measure="mse" there), deviance for logistic and poisson regression, and partiallikelihood for the Cox model. type.measure="class" applies to binomial and multinomial logistic regression only, and gives misclassification error. type.measure="auc" is for twoclass logistic regression only, and gives area under the ROC curve. type.measure="mse" or type.measure="mae" (mean absolute error) can be used by all models except the "cox"; they measure the deviation from the fitted mean to the response. 
seed 
seed 
nfolds 
number of crossvalidation's folds, default 10. 
foldid 
an optional vector of values between 1 and nfold identifying what fold each observation is in. If supplied, nfold can be missing. 
grouped 
This is an experimental argument, with default TRUE, and can be ignored by most users. For all models except the "cox", this refers to computing nfolds separate statistics, and then using their mean and estimated standard error to describe the CV curve. If grouped=FALSE, an error matrix is built up at the observation level from the predictions from the nfold fits, and then summarized (does not apply to type.measure="auc"). For the "cox" family, grouped=TRUE obtains the CV partial likelihood for the Kth fold by subtraction; by subtracting the log partial likelihood evaluated on the full dataset from that evaluated on the on the (K1)/K dataset. This makes more efficient use of risk sets. With grouped=FALSE the log partial likelihood is computed only on the Kth fold 
type.min 
parameter for chosing optimal model: 'lambda.min' value of lambda that gives minimum mean crossvalidated error (cvm). 'lambda.1se'  largest value of lambda such that error is within one standard error of the minimum. 
family 
family of the model, i.e. cox, glm,... 
verbose 
verbose 
... 
Further parameters 
Value
q.val 
minimal value of Q.func on the interval defined by bounds. Here, q.val is minimum mean crossvalidate d error (cvm) 
model 
model list

Author(s)
Natalia Becker natalia.becker at dkfz.de
References
Sill M., Hielscher T., Becker N. and Zucknick M. (2014), c060: Extended Inference with Lasso and ElasticNet Regularized Cox and Generalized Linear Models, Journal of Statistical Software, Volume 62(5), pages 1–22. doi:10.18637/jss.v062.i05