2010 Illinois Congressional Districts

[Jfer09]

Redistricting requirements

In Illinois, districts must, under Ill. Const. Art. IV, § 3:

1. be contiguous
2. have equal populations
3. be geographically compact

Interpretation of requirements

We enforce a maximum population deviation of 0.5%.

Data Sources

Data for Illinois comes from the ALARM Project's 2010 Redistricting Data Files.

Pre-processing Notes

No manual pre-processing decisions were necessary.

Simulation Notes

We sample 40,000 districting plans for Illinois across two independent runs of the SMC algorithm, and then thin the sample down to 5,000 plans. To balance county and municipality splits, we create pseudocounties for use in the county constraint. These are counties, outside of Cook and DuPage counties, which are the counties with populations larger than the target population for districts and thus necessarily split. Within Cook and DuPage counties counties, each municipality is its own pseudocounty as well.

Validation

n_black_perf n 1 1 788 2 2 3163 3 3 993 4 4 56

n_hisp_perf n 1 0 94 2 1 1780 3 2 2694 4 3 432

SMC: 5,000 sampled plans of 18 districts on 11,559 units
`adapt_k_thresh`=0.985 • `seq_alpha`=0.5
`est_label_mult`=1 • `pop_temper`=0

Plan diversity 80% range: 0.83 to 0.97

R-hat values for summary statistics:
   pop_overlap      total_vap       plan_dev      comp_edge    comp_polsby      pop_white 
     1.0066401      1.0040902      1.0053505      1.0016475      1.0037611      1.0112289 
     pop_black       pop_hisp       pop_aian      pop_asian       pop_nhpi      pop_other 
     1.0037227      1.0032911      1.0004030      1.0137069      1.0013844      1.0037937 
       pop_two      vap_white      vap_black       vap_hisp       vap_aian      vap_asian 
     1.0015511      1.0128236      1.0031318      1.0026999      1.0006780      1.0094117 
      vap_nhpi      vap_other        vap_two pre_16_dem_cli pre_16_rep_tru pre_20_dem_bid 
     1.0005052      1.0002026      1.0062377      1.0014587      1.0087195      1.0027107 
pre_20_rep_tru uss_16_dem_duc uss_16_rep_kir uss_20_dem_dur uss_20_rep_cur gov_18_dem_pri 
     1.0088780      1.0000684      1.0116457      1.0021719      1.0097080      1.0011217 
gov_18_rep_rau atg_18_dem_rao atg_18_rep_har sos_18_dem_whi sos_18_rep_hel         adv_16 
     1.0115692      1.0014222      1.0094231      1.0016785      1.0100770      1.0007123 
        adv_18         adv_20         arv_16         arv_18         arv_20  county_splits 
     1.0015364      1.0021613      1.0094719      1.0104310      1.0090490      1.0108989 
   muni_splits            ndv            nrv        ndshare          e_dvs         pr_dem 
     1.0096764      1.0017542      1.0092632      1.0117544      1.0117630      0.9998086 
         e_dem          pbias           egap 
     1.0092354      1.0033035      1.0090480 

Sampling diagnostics for SMC run 1 of 2 (20,000 samples)
         Eff. samples (%) Acc. rate Log wgt. sd   Max. unique Est. k 
Split 1    19,038 (95.2%)     21.1%        0.44 12,654 (100%)     14 
Split 2    18,702 (93.5%)     33.6%        0.52 12,458 ( 99%)      8 
Split 3    18,459 (92.3%)     40.3%        0.57 12,401 ( 98%)      6 
Split 4    18,296 (91.5%)     47.6%        0.60 12,383 ( 98%)      4 
Split 5    18,190 (90.9%)     45.9%        0.63 12,262 ( 97%)      4 
Split 6    17,994 (90.0%)     50.4%        0.65 12,161 ( 96%)      3 
Split 7    17,986 (89.9%)     54.1%        0.65 12,164 ( 96%)      2 
Split 8    17,755 (88.8%)     25.3%        0.67 12,181 ( 96%)      7 
Split 9    17,593 (88.0%)     30.5%        0.69 12,226 ( 97%)      5 
Split 10   17,493 (87.5%)     28.2%        0.70 12,155 ( 96%)      5 
Split 11   17,517 (87.6%)     19.4%        0.69 12,059 ( 95%)      7 
Split 12   17,510 (87.5%)     23.9%        0.68 11,913 ( 94%)      5 
Split 13   17,368 (86.8%)     26.1%        0.67 11,997 ( 95%)      4 
Split 14   17,086 (85.4%)     28.9%        0.66 11,923 ( 94%)      3 
Split 15   17,156 (85.8%)     17.2%        0.70 11,557 ( 91%)      5 
Split 16   16,589 (82.9%)     16.5%        0.75 11,210 ( 89%)      4 
Split 17   17,007 (85.0%)      7.3%        0.74 10,085 ( 80%)      3 
Resample    8,969 (44.8%)       NA%        0.75 13,817 (109%)     NA 

Sampling diagnostics for SMC run 2 of 2 (20,000 samples)
         Eff. samples (%) Acc. rate Log wgt. sd   Max. unique Est. k 
Split 1    19,034 (95.2%)     19.6%        0.45 12,613 (100%)     15 
Split 2    18,732 (93.7%)     30.4%        0.51 12,396 ( 98%)      9 
Split 3    18,488 (92.4%)     26.0%        0.57 12,359 ( 98%)     10 
Split 4    18,278 (91.4%)     37.8%        0.60 12,308 ( 97%)      6 
Split 5    18,136 (90.7%)     46.3%        0.63 12,285 ( 97%)      4 
Split 6    17,986 (89.9%)     29.5%        0.65 12,177 ( 96%)      7 
Split 7    17,835 (89.2%)     27.5%        0.67 12,228 ( 97%)      7 
Split 8    17,745 (88.7%)     38.8%        0.68 12,272 ( 97%)      4 
Split 9    17,747 (88.7%)     30.8%        0.68 12,157 ( 96%)      5 
Split 10   17,677 (88.4%)     38.7%        0.69 12,147 ( 96%)      3 
Split 11   17,632 (88.2%)     42.7%        0.68 12,087 ( 96%)      2 
Split 12   17,620 (88.1%)     40.0%        0.68 12,113 ( 96%)      2 
Split 13   17,698 (88.5%)     26.2%        0.66 11,988 ( 95%)      4 
Split 14   17,322 (86.6%)     28.6%        0.65 11,914 ( 94%)      3 
Split 15   17,218 (86.1%)     30.0%        0.68 11,621 ( 92%)      2 
Split 16   17,379 (86.9%)     24.2%        0.70 11,170 ( 88%)      2 
Split 17   17,717 (88.6%)      8.8%        0.67  9,970 ( 79%)      2 
Resample   11,911 (59.6%)       NA%        0.67 14,580 (115%)     NA 

Checklist

• [x] I have followed the instructions
• [x] I have updated the tracker
• [x] All TODO lines from the template code have been removed
• [x] I have merged in the main branch and then recalculated summary statistics
• [x] I have run enforce_style() to format my code
• [x] The documentation copied above is up-to-date
• [x] There are no data files in this pull request
• [x] None of the file output paths (for the redist_map and redist_plans objects, and summary statistics) have been edited

delete this line and all the tags except the reviewers you need @CoryMcCartan @christopherkenny

[CoryMcCartan]

Looks good to me! That last diagnostic plot is very helpful in showing that with the small exception of District 4, the sampled plans are in the same region as the enacted along both BVAP and HVAP dimensions. @christopherkenny on to you!

[christopherkenny]

Yeah, this looks in line with the geographic + coalition discussion from last time, so I'm content.