d04 aggregate Ruhela: non-majority religion -> custodial deaths

Usage

morie_otis_analyze_d04_ruhela_aggregate(data, out_dir = NULL)

morie_otis_analyze_d04_mrm_aggregate(data, out_dir = NULL)

Arguments

data: d04 data.frame.
out_dir: Optional.

Value

morie_otis_analysis_result.

Examples

# \donttest{
otis_d04 <- morie_synth_otis("d04", n = 120L, seed = 1L)
morie_otis_analyze_d04_ruhela_aggregate(otis_d04)
#> OTIS d04 -- Aggregate RF: Non-majority religion -> Number of custodial deaths
#> =============================================================================
#>   Source file                            d04_deaths_in_custody_religion.csv
#>   Dataset id                             d04
#>   Treatment column                       T_minority_religion
#>   Outcome (count)                        Number_CustodialDeaths
#>   Year FE                                Year
#>   Covariate FEs                          none
#>   Cluster group (GEE)                    --
#>   Cells                                  120
#>   Total outcome count                    5101
#>   Overdispersion (Poisson AIC - NB AIC)  1114.2
#> 
#> Aggregate Ruhela formulation -- Poisson + NB IRR for treatment effect on count outcome:
#>   Family   Coefficient                   IRR     95% CI          p-value   AIC     Notes
#>   ----------------------------------------------------------------------------------------------------
#>   Poisson  factor(T_minority_religion)1  0.9121  [0.856, 0.973]  4.93e-03  2233.7  n=120, total_y=5101
#>   NB       factor(T_minority_religion)1  0.9048  [0.688, 1.190]  4.74e-01  1119.5  n=120, total_y=5101
#> 
#> Aggregate RF on d04: religious-minority death counts.
#> 
#> 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. 
# }