Per-fiscal-year full-DLRM Ruhela formulation driver. — morie_otis_analyze_ruhela_per

Runs the complete 10-estimator DLRM separately on each fiscal year. This is a heavy operation (~7x the single-year runtime).

Usage

morie_otis_analyze_ruhela_per_year(
  data,
  ds_id,
  treatment,
  outcome,
  covariates,
  year_col = "EndFiscalYear",
  cluster_col = "EndFiscalYear",
  out_dir = NULL
)

Arguments

data: Long-format data.frame with treatment / outcome / cov.
ds_id: Dataset id label.
treatment: Treatment column name.
outcome: Outcome column name.
covariates: Character vector of covariate column names.
year_col: Year column (default "EndFiscalYear").
cluster_col: Cluster axis for SE, or NULL.
out_dir: Optional output directory.

Value

morie_otis_analysis_result.

Examples

# \donttest{
morie_otis_analyze_ruhela_per_year(df, ds_id = "a01",
  treatment = "T", outcome = "Y", covariates = c("Gender"))
#> morie_otis_analyze_ruhela_per_year(a01) -- not yet ported
#> =========================================================
#>   status          stub
#>   reason          morie_otis_analyze_ruhela_per_year(a01): not yet ported to R (per-year DLRM × estimator triangulation)
#>   recommendation  Use the Python implementation in src/morie/otis_all_analyze.py for now.
#> 
#> Warning: morie_otis_analyze_ruhela_per_year(a01): not yet ported to R (per-year DLRM × estimator triangulation) 
#> morie_otis_analyze_ruhela_per_year(a01): not yet ported to R (per-year DLRM × estimator triangulation) 
# }