Closed mzhao80 closed 1 year ago
In Missouri, according to Mo. Const. art. III, § 2, districts must:
We enforce a maximum population deviation of 0.5%. We use a standard algorithmic county constraint. We add a hinge Gibbs constraint targeting one majority-minority district to comply with VRA requirements and match the number in the enacted plan.
Data for Missouri comes from the ALARM Project's Redistricting Data Files.
No manual pre-processing decisions were necessary.
We sample 5,000 districting plans for Missouri across two independent runs of the SMC algorithm.
SMC: 5,000 sampled plans of 8 districts on 4,813 units `adapt_k_thresh`=0.985 • `seq_alpha`=0.95 `est_label_mult`=1 • `pop_temper`=0 Plan diversity 80% range: 0.50 to 0.77 R-hat values for summary statistics: vap_black pop_overlap total_vap plan_dev comp_edge comp_polsby pop_white 1.0019362 1.0001980 1.0057206 1.0114052 1.0002806 1.0040337 1.0029391 pop_black pop_hisp pop_aian pop_asian pop_nhpi pop_other pop_two 1.0021549 1.0017776 1.0078128 1.0162107 1.0040745 0.9999582 1.0016358 vap_white vap_hisp vap_aian vap_asian vap_nhpi vap_other vap_two 1.0059124 1.0017963 1.0036996 1.0160445 1.0015127 1.0008652 1.0018242 pre_16_rep_tru pre_16_dem_cli pre_20_rep_tru pre_20_dem_bid uss_16_rep_blu uss_16_dem_kan uss_18_rep_haw 1.0007565 1.0026979 1.0002460 1.0025551 1.0004420 1.0011973 1.0003595 uss_18_dem_mcc gov_16_rep_gre gov_16_dem_kos gov_20_rep_par gov_20_dem_gal atg_16_rep_haw atg_16_dem_hen 1.0019069 1.0003949 1.0009932 1.0001194 1.0018208 1.0001550 1.0018807 atg_20_rep_sch atg_20_dem_fin sos_16_rep_ash sos_16_dem_smi sos_20_rep_ash sos_20_dem_fal adv_16 1.0000752 1.0027933 1.0002822 1.0024667 1.0001090 1.0029881 1.0020217 adv_18 adv_20 arv_16 arv_18 arv_20 county_splits muni_splits 1.0019069 1.0027655 1.0002214 1.0003595 1.0000291 1.0010467 1.0032203 ndv nrv ndshare e_dvs e_dem pbias egap 1.0017142 1.0001595 1.0003798 1.0003734 0.9998732 1.0014939 0.9999342 Sampling diagnostics for SMC run 1 of 2 (5,000 samples) Eff. samples (%) Acc. rate Log wgt. sd Max. unique Est. k Split 1 3,026 (60.5%) 12.2% 0.41 3,173 (100%) 13 Split 2 3,029 (60.6%) 18.0% 0.47 2,733 ( 86%) 8 Split 3 2,814 (56.3%) 9.7% 0.51 2,783 ( 88%) 13 Split 4 2,975 (59.5%) 14.1% 0.54 2,766 ( 88%) 8 Split 5 3,124 (62.5%) 16.1% 0.52 2,819 ( 89%) 6 Split 6 3,225 (64.5%) 17.7% 0.56 2,751 ( 87%) 4 Split 7 2,720 (54.4%) 6.1% 0.56 2,498 ( 79%) 4 Resample 2,466 (49.3%) NA% 0.66 3,706 (117%) NA Sampling diagnostics for SMC run 2 of 2 (5,000 samples) Eff. samples (%) Acc. rate Log wgt. sd Max. unique Est. k Split 1 3,019 (60.4%) 13.5% 0.42 3,152 (100%) 12 Split 2 2,961 (59.2%) 20.7% 0.46 2,728 ( 86%) 7 Split 3 2,851 (57.0%) 20.5% 0.52 2,808 ( 89%) 6 Split 4 2,998 (60.0%) 25.0% 0.53 2,774 ( 88%) 4 Split 5 3,050 (61.0%) 27.5% 0.53 2,759 ( 87%) 3 Split 6 3,437 (68.7%) 26.0% 0.54 2,696 ( 85%) 2 Split 7 3,088 (61.8%) 9.7% 0.55 2,468 ( 78%) 2 Resample 2,898 (58.0%) NA% 0.63 3,734 (118%) NA
TODO
enforce_style()
redist_map
redist_plans
@CoryMcCartan
BVAP check
Redistricting requirements
In Missouri, according to Mo. Const. art. III, § 2, districts must:
Algorithmic Constraints
We enforce a maximum population deviation of 0.5%. We use a standard algorithmic county constraint. We add a hinge Gibbs constraint targeting one majority-minority district to comply with VRA requirements and match the number in the enacted plan.
Data Sources
Data for Missouri comes from the ALARM Project's Redistricting Data Files.
Pre-processing Notes
No manual pre-processing decisions were necessary.
Simulation Notes
We sample 5,000 districting plans for Missouri across two independent runs of the SMC algorithm.
Validation
Checklist
TODO
lines from the template code have been removedenforce_style()
to format my coderedist_map
andredist_plans
objects, and summary statistics) have been edited@CoryMcCartan