Covariates are the independent variables which you want to always be included in your statistical models - regardless of the groups, outcomes, or predictors. Only one set of covariates can be supplied. If you want to test multiple sets of covariates, then you should specify them as predictors or you should create a new, separate model. This function supports both string inputs and actual variables. The inputs should be separated by a comma, where all variables together is the single covariate set.
Arguments
- .model
an aba model. The model for which you want to set covariates.
- ...
strings or variables. This comma-separated collection of values will become the single set of covariates. If you supply actual variables, then the data of the aba model should already be set.
- .include_basic
logical. Whether to fit a model of only covariates ("basic" model).
Examples
data <- adnimerge %>% dplyr::filter(VISCODE == 'bl')
# set with variables
model <- aba_model() %>%
set_data(data) %>%
set_covariates(AGE, GENDER, EDUCATION)
# supply strings - data does not need to be set first here. But it will
# result in an error if these variables do not éxist in the eventual data.
model <- aba_model() %>%
set_covariates('AGE', 'GENDER', 'EDUCATION')