No manual pre-processing decisions were necessary.
Simulation Notes
We sample 5,000 districting plans for Mississippi, across two independent runs of the SMC algorithm.
We apply a hinge Gibbs constraint of strength 25 to encourage drawing a majority black district.
Validation
MC: 5,000 sampled plans of 4 districts on 1,834 units
`adapt_k_thresh`=0.985 • `seq_alpha`=0.5
`est_label_mult`=1 • `pop_temper`=0
Plan diversity 80% range: 0.33 to 0.65
R-hat values for summary statistics:
pop_overlap total_vap plan_dev comp_edge comp_polsby pop_hisp
1.0161978 1.0135821 1.0017838 1.0059392 1.0131546 1.0231597
pop_white pop_black pop_aian pop_asian pop_nhpi pop_other
1.0046979 1.0001948 1.0195683 1.0105299 1.0098101 1.0225349
pop_two vap_hisp vap_white vap_black vap_aian vap_asian
1.0308993 1.0091235 1.0040708 1.0006973 1.0219826 1.0121113
vap_nhpi vap_other vap_two pre_16_rep_tru pre_16_dem_cli uss_18_rep_wic
1.0173080 1.0161155 1.0123284 1.0010476 1.0022840 1.0029217
uss_18_dem_bar uss_r18_rep_hyd uss_r18_dem_esp pre_20_rep_tru pre_20_dem_bid uss_20_rep_hyd
1.0036974 1.0024034 1.0032830 1.0021244 1.0028947 1.0014444
uss_20_dem_esp arv_16 adv_16 arv_18 adv_18 arv_20
1.0043998 1.0010476 1.0022840 1.0029217 1.0036974 1.0016682
adv_20 county_splits muni_splits ndv nrv ndshare
1.0030305 1.0025706 1.0197658 1.0060115 1.0013998 1.0071866
e_dvs e_dem pbias egap
1.0071928 0.9999397 1.0004984 1.0205619
Sampling diagnostics for SMC run 1 of 2 (2,500 samples)
Eff. samples (%) Acc. rate Log wgt. sd Max. unique Est. k
Split 1 1,893 (75.7%) 11.8% 0.33 1,560 ( 99%) 9
Split 2 1,362 (54.5%) 17.1% 0.75 1,458 ( 92%) 5
Split 3 1,270 (50.8%) 9.2% 1.12 1,186 ( 75%) 3
Resample 490 (19.6%) NA% 3.08 967 ( 61%) NA
Sampling diagnostics for SMC run 2 of 2 (2,500 samples)
Eff. samples (%) Acc. rate Log wgt. sd Max. unique Est. k
Split 1 1,884 (75.3%) 9.0% 0.32 1,587 (100%) 12
Split 2 1,413 (56.5%) 12.8% 0.68 1,440 ( 91%) 7
Split 3 1,105 (44.2%) 6.9% 1.02 1,246 ( 79%) 4
Resample 300 (12.0%) NA% 3.09 855 ( 54%) NA
• Watch out for low effective samples, very low acceptance rates (less than 1%), large std. devs. of the
log weights (more than 3 or so), and low numbers of unique plans. R-hat values for summary statistics
should be between 1 and 1.05.
Redistricting requirements
In Mississippi, under Mississippi Code 5-3-123 and Committee agreement, districts must:
Interpretation of requirements
We enforce a maximum population deviation of 0.5%. We ensure that there is a majority minority district with at least 55% VAP.
Data Sources
Data for Mississippi comes from the ALARM Project's 2020 Redistricting Data Files.
Pre-processing Notes
No manual pre-processing decisions were necessary.
Simulation Notes
We sample 5,000 districting plans for Mississippi, across two independent runs of the SMC algorithm. We apply a hinge Gibbs constraint of strength 25 to encourage drawing a majority black district.
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