regress: Compute linear regression

Description

Computes linear regression for all independent variables on the specified dependent variable. Linear modeling of multiple independent variables uses stepwise regression modeling. If specified, preconditions for (multi-)collinearity and for homoscedasticity are checked.

Usage

regress(
  data,
  dependent_var,
  ...,
  check_independenterrors = FALSE,
  check_multicollinearity = FALSE,
  check_homoscedasticity = FALSE
)

Value

a tdcmm model

Arguments

data: a tibble or a tdcmm model
dependent_var: The dependent variable on which the linear model is fitted. Specify as column name.
...: Independent variables to take into account as (one or many) predictors for the dependent variable. Specify as column names. At least one has to be specified.
check_independenterrors: if set, the independence of errors among any two cases is being checked using a Durbin-Watson test
check_multicollinearity: if set, multicollinearity among all specified independent variables is being checked using the variance inflation factor (VIF) and the tolerance (1/VIF); this check can only be performed if at least two independent variables are provided, and all provided variables need to be numeric
check_homoscedasticity: if set, homoscedasticity is being checked using a Breusch-Pagan test

Examples

Run this code

WoJ %>% regress(autonomy_selection, ethics_1)
WoJ %>% regress(autonomy_selection, work_experience, trust_government)

Run the code above in your browser using DataLab