c02 aggregate Ruhela: Female -> RC (institution GEE)

Usage

morie_otis_analyze_c02_ruhela_aggregate(data, out_dir = NULL)

morie_otis_analyze_c02_mrm_aggregate(data, out_dir = NULL)

Arguments

data: c02 data.frame.
out_dir: Optional.

Value

morie_otis_analysis_result.

Examples

# \donttest{
otis_c02 <- morie_synth_otis("c02", n = 120L, seed = 1L)
morie_otis_analyze_c02_ruhela_aggregate(otis_c02)
#> OTIS c02 -- Aggregate RF, institution-clustered: Female -> Individuals in RC
#> ============================================================================
#>   Source file                            c02_individuals_in_segregation_and_restrictive_confinement_by_institution.csv
#>   Dataset id                             c02
#>   Treatment column                       T_female
#>   Outcome (count)                        NumberIndividuals_RestrictiveConfinement
#>   Year FE                                EndFiscalYear
#>   Covariate FEs                          Region_MostRecentPlacement
#>   Cluster group (GEE)                    Institution_MostRecentPlacement
#>   Cells                                  120
#>   Total outcome count                    4590
#>   Overdispersion (Poisson AIC - NB AIC)  1660.7
#> 
#> 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  1.0125  [0.954, 1.075]  6.83e-01  2792.1  n=120, total_y=4590
#>   NB                                                           factor(T_female)1  0.973   [0.716, 1.322]  8.61e-01  1131.4  n=120, total_y=4590
#>   GEE-Poisson (cluster:Institution_MostRecentPlacement, Exch)  factor(T_female)1  1.011   [0.846, 1.209]  9.05e-01  --      groups=25, n_obs=120
#> 
#> Aggregate RF on c02 with institution as GEE cluster group. Marginal-model analogue of glmmTMB nbinom2 random-intercept.
#> 
#> 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. 
# }