Fit multiple mixed effects models containing different combination of fractional polynomials

This function enables you to fit multiple models with different combinations of polynomial terms and compares the fit.

Usage

dh.lmeMultPoly(
  df = NULL,
  formulae = NULL,
  poly_names = NULL,
  conns = NULL,
  checks = TRUE
)

Arguments

df

Character specifying a server-side data frame.

formulae

Character vector containing model formulae to fit.

poly_names

Character vector of names for the models specified in formulae

conns

DataSHIELD connections object.

checks

Logical; if TRUE checks are performed prior to running the function. Default is TRUE.

Value

List containing three elements:

• models = List of objects returned by ds.lmerSLMA for each model fitted.

• convergence = Tibble providing information on convergence problems or error for each model fitted.

• fit = Tibble with columns containing negative loglikehood statistic for each cohort and rows for each model fitted. An additional column provides the sum of the loglikelihoods across cohorts.

See also

Other trajectory functions: dh.makeAgePolys(), dh.makeLmerForm(), dh.predictLmer(), dh.trimPredData(), dh.zByGroup()