R6 Class representing the Goodness-of-Fit test for (linear) models.

This class can test the null hypothesis that data follows a particular linear model, i.e. classical linear models, generalized linear models or models of the type \(m(\beta^\top X) + \epsilon\).

Methods

Public methods

• GOF_model_test$new()

• GOF_model_test$get_Rn1_org()

• GOF_model_test$get_Rn1_boot()

• GOF_model_test$get_pvalue()

• GOF_model_test$clone()

---

Method new()

Usage

GOF_model_test$new(
  model,
  data,
  nmb_boot_samples,
  y_name,
  Rn1_statistic,
  gof_model_info_extractor,
  gof_model_resample
)

Arguments

model

a fitted model

data

used to fit model

nmb_boot_samples

integer specifying the number of bootstrap samples to perform

y_name

string specifying the name of the dependent variable in in data

Rn1_statistic

statistic used to map the marked empirical process to the real line. Needs to be an instance of the class that implements Rn1_statistic

gof_model_info_extractor

an instance that implements GOF_model_info_extractor in order to apply it to model

gof_model_resample

an instance that implements GOF_model_resample in order to apply it to model

Returns

An instance of the Class

---

Method get_Rn1_org()

calculates the marked empricial process for model

Usage

GOF_model_test$get_Rn1_org()

Returns

vector ordered by the inner product of the estimated parameter and the independent variables

---

Method get_Rn1_boot()

calculates the marked empricial process for the resampled versions of model

Usage

GOF_model_test$get_Rn1_boot()

Returns

list of length nmb_boot_samples where every element is a vector ordered by the inner product of the estimated parameter and the dependent variables

---

Method get_pvalue()

p-value for Goodness-of-Fit-test for model

Usage

GOF_model_test$get_pvalue()

Returns

p-value for the null hypothesis that the dependent variable was generated according to model

---

Method clone()

The objects of this class are cloneable with this method.

Usage

GOF_model_test$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.