c04 aggregate Ruhela: Indigenous -> RC (by region)

Usage

morie_otis_analyze_c04_ruhela_aggregate(data, out_dir = NULL)

morie_otis_analyze_c04_mrm_aggregate(data, out_dir = NULL)

Arguments

data: c04 data.frame.
out_dir: Optional.

Value

morie_otis_analysis_result.

Examples

# \donttest{
otis_c04 <- morie_synth_otis("c04", n = 120L, seed = 1L)
morie_otis_analyze_c04_ruhela_aggregate(otis_c04)
#> OTIS c04 -- Aggregate RF: Indigenous -> Individuals in RC, by region
#> ====================================================================
#>   Source file                            c04_individuals_in_segregation_and_restrictive_confinement_race_by_region.csv
#>   Dataset id                             c04
#>   Treatment column                       T_indigenous
#>   Outcome (count)                        NumberIndividuals_RestrictiveConfinement
#>   Year FE                                EndFiscalYear
#>   Covariate FEs                          Region_MostRecentPlacement
#>   Cluster group (GEE)                    --
#>   Cells                                  120
#>   Total outcome count                    4395
#>   Overdispersion (Poisson AIC - NB AIC)  1660
#> 
#> Aggregate Ruhela formulation -- Poisson + NB IRR for treatment effect on count outcome:
#>   Family   Coefficient            IRR     95% CI          p-value   AIC     Notes
#>   ---------------------------------------------------------------------------------------------
#>   Poisson  factor(T_indigenous)1  1.0215  [0.928, 1.125]  6.65e-01  2780.8  n=120, total_y=4395
#>   NB       factor(T_indigenous)1  1.0867  [0.663, 1.783]  7.42e-01  1120.8  n=120, total_y=4395
#> 
#> Aggregate RF on c04 testing within-region Indigenous overrepresentation in RC.
#> 
#> IRR > 1 ==> treatment increases the count rate; IRR < 1 ==> treatment decreases it. Concordance between Poisson and NB indicates equidispersion; large gap (Poisson AIC > NB AIC) indicates overdispersion -- trust NB. 
# }