set_additive_error_model {pharmr}

set_additive_error_model

Description

Set an additive error model. Initial estimate for new sigma is :math:⁠(min(DV)/2)²⁠.

The error function being applied depends on the data transformation. The table displays some examples.

+————————+—————————————-+ | Data transformation | Additive error | +========================+========================================+ | :math:y | :math:f + epsilon_1 | +————————+—————————————-+ | :math:log(y) | :math:⁠log(f) + frac{epsilon_1}{f}⁠ | +————————+—————————————-+

Usage

set_additive_error_model(model, dv = NULL, data_trans = NULL, series_terms = 2)

Arguments

model

(Model) Set error model for this model

dv

(str or numeric (optional)) Name or DVID of dependent variable. NULL for the default (first or only)

data_trans

(str (optional)) A data transformation expression or NULL (default) to use the transformation specified by the model. Series expansion will be used for approximation.

series_terms

(numeric) Number of terms to use for the series expansion approximation for data transformation.

Value

(Model) Pharmpy model object

See Also

set_proportional_error_model : Proportional error model

set_combined_error_model : Combined error model

Examples

## Not run: 
model <- load_example_model("pheno")
model$statements$find_assignment("Y")
model <- set_additive_error_model(model)
model$statements$find_assignment("Y")
model <- load_example_model("pheno")
model$statements$find_assignment("Y")
model <- set_additive_error_model(model, data_trans="log(Y)")
model$statements$find_assignment("Y")

## End(Not run)