search.rfunc: Create a Model Set for an R Function

In ldt: Automated Uncertainty Analysis

Create a Model Set for an R Function

Description

Use this model to create a model set for an R function.

Usage

search.rfunc(
  data = get.data(),
  combinations = get.combinations(),
  metrics = get.search.metrics(),
  modelChecks = get.search.modelchecks(),
  items = get.search.items(),
  options = get.search.options(),
  rFuncName,
  length1,
  isInnerExogenous
)

Arguments

data	A list that determines data and other required information for the search process. Use get.data() function to generate it from a matrix or a data.frame.
combinations	A list that determines the combinations of endogenous and exogenous variables in the search process. Use get.combinations() function to define it.
metrics	A list of options for measuring performance. Use get.search.metrics function to get them.
modelChecks	A list of options for excluding a subset of the model set. See and use get.search.modelchecks function to get them.
items	A list of options for specifying the purpose of the search. See and use get.search.items function to get them.
options	A list of extra options for performing the search. See and use get.search.options function to get them.
rFuncName	Name of a function that uses column indices and number of endogenous variables with respect to data. It should estimate a model and return a list with required performance statistics. See details.
length1	An integer for the length of requested information. This can be the number of exogenous variables.
isInnerExogenous	If TRUE, exogenous indices are defined by innerGroups in the combinations argument.

Details

The central part of calling this function is to write a function with rFuncName name. This function must have the following arguments:

• columnIndices: determines the variables to be used in the current iteration. These indices point to the column of data$data matrix. E.g., you can create a matrix of available data by using data$data[,colIndices]. It contains weight column index (at numEndo+1), if data$hasWeight is TRUE.

• numEndo: can be used to divide the columnIndices into endogenous and exogenous indices.

• data, metrics, modelChecks, items: The arguments of current function which are passed to this function.

The rFuncName function should use these arguments and estimate or predict by using any available R function.

This function must return a List with the following items:

• error (Character string or NULL): It not NULL or empty, it is considered as a failed estimation with the given message.

• metrics (Numeric Matrix): Model performance for each target variable. Available target variables must be in the columns and metrics in the rows.

• extra (Numeric Vector or NULL): Extra information in form of integers, which defines the current model.

• type1means (Numeric Matrix or NULL): Means of type1 (coefficients or predictions) for each target variable. Target variables must be in the columns. Make sure to skip the rows which the model does not present any information.

• type1vars (Numeric Matrix or NULL): similar to type1means but for reporting the variances.

Value

A nested list with the following members:

counts	Information about the expected number of models, number of estimated models, failed estimations, and some details about the failures.
results	A data frame with requested information in items list.
info	The arguments and some general information about the search process such as the elapsed time.

Note that the output does not contain any estimation results, but minimum required data to estimate the models (Use summary() function to get the estimation).

ldt documentation built on Sept. 11, 2024, 5:25 p.m.