Compare fitted 2D-Gaussians and determine the best-fitting model

compare_gaussian_fits(fit_objects_list, comparison_method = "rmse")

Arguments

fit_objects_list	A list of outputs from `fit_gaussian_2D()`. See Details for more
comparison_method	One of "rmse", "rss", or "AIC"; what metric should be used to determine the "best-fitting" Gaussian?

Value

A list with the components:

"preferred_model" A character indicating the name of the preferred model (or if a named list was not provided, a model number is given in the order of the original supplied list).
"comparison_table" A data.frame detailing the rss, rmse, deviance, , AIC, R2, and adjusted R2 of the fitted models. The data.frame is sorted by the comparison_method that was selected.

Details

For the argument fit_objects_list, a list of fitted model objects (output from fit_gaussian_2D()) can simply be combined via list(). Naming the list is optional; should you supply names, the output of compare_gaussian_fits() will refer to specific models by these names.

Author

Vikram B. Baliga

Examples

if (interactive()) {
  library(gaussplotR)

  ## Load the sample data set
  data(gaussplot_sample_data)

  ## The raw data we'd like to use are in columns 1:3
  samp_dat <-
    gaussplot_sample_data[,1:3]

  ## Fit a variety of different models
  gauss_fit_ue <-
    fit_gaussian_2D(samp_dat)
  gauss_fit_uel <-
    fit_gaussian_2D(samp_dat, method = "elliptical_log")
  gauss_fit_cir <-
    fit_gaussian_2D(samp_dat, method = "circular")

  ## Combine the outputs into a list
  models_list <-
    list(
      unconstrained_elliptical = gauss_fit_ue,
      unconstrained_elliptical_log = gauss_fit_uel,
      circular = gauss_fit_cir
    )

  ## Compare via rmse
  models_compared <-
    compare_gaussian_fits(
      fit_objects_list = models_list,
      comparison_method = "rmse" ## the default
    )
}