dsROCGLM: Calculate Probit Regression on Server

In difuture-lmu/dsROCGLM: ROC and calibration analysis for DataSHIELD

Calculate Probit Regression on Server

Description

ROC-GLM function for DataSHIELD. The function prepares the data on the server and fits the model. The model returned by the function contains ROC-GLM as parametrized model.

Usage

dsROCGLM(
  connections,
  truth_name,
  pred_name,
  trace = TRUE,
  clean_server = TRUE,
  alpha = 0.05,
  dat_name = "D",
  seed_object = NULL,
  ...
)

Arguments

connections	('DSI::connection') Connection to an OPAL server.
truth_name	('character(1L)') Character containing the name of the vector of 0-1-values encoded as integer or numeric.
pred_name	('character(1L)') Character containing the name of the vector of probabilities.
trace	('logical(1L)') If 'TRUE' (default), information about the progress is shown.
clean_server	('logical(1L)') Set to 'TRUE' (default) if all temprary data stored on the server should be removed when the fitting is finished.
alpha	('numeric(1L)') Significance level alpha for confidence interval (default is '0.05').
dat_name	('character(1L)') Name of the data set on the servers..
seed_object	('character(1L)') Name of an object which is used to add a seed based on an object.
...	Additional arguments passed to 'dsL2Sens' (connections and pred_name is already set).

Value

List with estimated parameter, number of iterations, and the deviance when the algorithm is stopped.

Author(s)

Daniel S.

difuture-lmu/dsROCGLM documentation built on March 24, 2024, 1:07 p.m.