estimate_qra_optimized: Estimate qra parameters by optimizing weighted interval score...

In reichlab/covidEnsembles: What the Package Does (One Line, Title Case)

Estimate qra parameters by optimizing weighted interval score loss

Description

Estimate qra parameters by optimizing weighted interval score loss

Usage

estimate_qra_optimized(
  qfm_train,
  y_train,
  quantile_groups,
  qra_model = c("convex_per_model", "unconstrained_per_model",
    "rescaled_convex_per_model", "rel_wis_weighted_median"),
  backend = c("optim", "NlcOptim", "grid_search"),
  max_weight = NULL
)

Arguments

qfm_train	QuantileForecastMatrix with training set predictions from component models
y_train	numeric vector of responses for training set
quantile_groups	Vector of group labels for quantiles, having the same length as the number of quantiles. Common labels indicate that the ensemble weights for the corresponding quantile levels should be tied together. Default is rep(1,length(quantiles)), which means that a common set of ensemble weights should be used across all levels. This is the argument tau_groups for quantgen::quantile_ensemble, and may only be supplied if ⁠backend = 'quantgen⁠
qra_model	quantile averaging model
backend	implementation used for estimation; currently either 'optim', using L-BFGS-B as provided by the optim function in R, or 'NlcOptim', using NlcOptim::solnl, or 'grid_search', using covidEnsemble::grid_search
max_weight	numeric value for maximum weight. Ignored unless qra_model is rel_wis_weighted_median or rel_wis_weighted mean and backend is grid_search

Value

object of class qra_fit

reichlab/covidEnsembles documentation built on Jan. 31, 2024, 7:21 p.m.