b06 aggregate Ruhela: Disciplinary reason -> seg placements

Usage

morie_otis_analyze_b06_ruhela_aggregate(data, out_dir = NULL)

morie_otis_analyze_b06_mrm_aggregate(data, out_dir = NULL)

Arguments

data: b06 data.frame.
out_dir: Optional.

Value

morie_otis_analysis_result.

Examples

# \donttest{
otis_b06 <- morie_synth_otis("b06", n = 120L, seed = 1L)
morie_otis_analyze_b06_ruhela_aggregate(otis_b06)
#> OTIS b06 -- Aggregate Ruhela formulation: Disciplinary reason -> seg placements
#> ===============================================================================
#>   Source file                            b06_segregation_placements_reason_for_placement_by_institution.csv
#>   Dataset id                             b06
#>   Treatment column                       T_disciplinary
#>   Outcome (count)                        Number_SegregationPlacements
#>   Year FE                                EndFiscalYear
#>   Covariate FEs                          Gender, Region_AtTimeOfPlacement
#>   Cluster group (GEE)                    Institution_AtTimeOfPlacement
#>   Cells                                  120
#>   Total outcome count                    4773
#>   Overdispersion (Poisson AIC - NB AIC)  1162.5
#> 
#> 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_disciplinary)1  1.0452  [0.939, 1.164]  4.21e-01  2282.1  n=120, total_y=4773
#>   NB                                                         factor(T_disciplinary)1  1.0327  [0.647, 1.649]  8.93e-01  1119.6  n=120, total_y=4773
#>   GEE-Poisson (cluster:Institution_AtTimeOfPlacement, Exch)  factor(T_disciplinary)1  1.0459  [0.829, 1.320]  7.06e-01  --      groups=25, n_obs=120
#> 
#> Aggregate RF on b06 testing whether disciplinary segregation reasons produce more placements than non-disciplinary.
#> 
#> 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. 
# }