Initialization

The class is initialized by passing the following arguments:

regression_procedure

- a fully qualified name of the module/class in which the regression is implemented (see Section 24.5.5). The default value is 'opus_core.linear_regression'.

submodel_string

- If model contains submodels, this character string specifies what attribute of the observation set determines those submodels. Default is None.

run_config

- A collection of additional arguments that control a simulation run. It should be a dictionary or an instance of class Resources. Default is None.

estimate_config

- A collection of additional arguments that control an estimation run. It should be a dictionary or an instance of class Resources. Default is None.

dataset_pool

- A pool of datasets needed for computation of variables. Default is None.

From the argument regression_procedure the initialization method creates a class attribute regression, using RegressionModelFactory (see Section 24.5). The remaining arguments are set as class properties.