b08 aggregate Ruhela: Female -> median seg duration (institution-clustered)

Usage

morie_otis_analyze_b08_ruhela_aggregate(data, out_dir = NULL)

morie_otis_analyze_b08_mrm_aggregate(data, out_dir = NULL)

Arguments

data: b08 data.frame.
out_dir: Optional.

Value

morie_otis_analysis_result.

Examples

# \donttest{
otis_b08 <- morie_synth_otis("b08", n = 120L, seed = 1L)
morie_otis_analyze_b08_ruhela_aggregate(otis_b08)
#> OTIS b08 -- Aggregate Ruhela formulation: Female -> median seg duration
#> =======================================================================
#>   Source file                            b08_segregation_placements_consecutive_durations_by_institution.csv
#>   Dataset id                             b08
#>   Treatment column                       T_female
#>   Outcome (count)                        NumberConsecutiveDays_Segregation
#>   Year FE                                EndFiscalYear
#>   Covariate FEs                          Region_AtTimeOfPlacement
#>   Cluster group (GEE)                    Institution_AtTimeOfPlacement
#>   Cells                                  53
#>   Total outcome count                    2276
#>   Overdispersion (Poisson AIC - NB AIC)  467.4
#> 
#> Aggregate Ruhela formulation -- Poisson + NB IRR + GEE clustered for treatment effect on count outcome:
#>   Family                                                     Coefficient        IRR     95% CI          p-value   AIC    Notes
#>   ------------------------------------------------------------------------------------------------------------------------------------------
#>   Poisson                                                    factor(T_female)1  1.1989  [1.097, 1.310]  6.24e-05  981.3  n=53, total_y=2276
#>   NB                                                         factor(T_female)1  1.2198  [0.830, 1.792]  3.11e-01  514    n=53, total_y=2276
#>   GEE-Poisson (cluster:Institution_AtTimeOfPlacement, Exch)  factor(T_female)1  1.1131  [0.811, 1.527]  5.06e-01  --     groups=25, n_obs=53
#> 
#> Aggregate RF on b08 testing gender disparity in median segregation duration; institution as GEE cluster group.
#> 
#> 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. 
# }