Re-run 2020 Minnesota Congressional Districts

Redistricting requirements

In Minnesota, districts must:

be convenient and contiguous (Minn. Const. art. IV, § 3)
be substantially equal in population (Minn. Stat. 2.91)
not divide political subdivisions more than necessary to meet constitutional requirements (Minn. Stat. 2.91)

Furthermore, the following principles guide redistricting in Minnesota which stipulate that districts must:

have populations as nearly as equal as practical
preserve communities of interest
not abridge voting rights of minority groups
not unduly protect nor defeat incumbents (Order of the Special Redistricting Panel, Hippert vs. Ritchie, No. A11-152)

Interpretation of requirements

We enforce a maximum population deviation of 0.1%. We use a pseudo-county constraint described below which attempts to mimic the norms in Minnesota of generally preserving county, city, and township boundaries.

Data Sources

Data for Minnesota comes from the ALARM Project's 2020 Redistricting Data Files. Data for Minnesota's 2020 congressional district map comes from the Minnesota Legislature's Geographic Information Services

Pre-processing Notes

No manual pre-processing decisions were necessary.

Simulation Notes

We sample 5,000 districting plans for Minnesota across two independent runs of the SMC algorithm. We use a pseudo-county constraint to limit the county and municipality (i.e., city and township) splits. Municipality lines are used in Anoka County, Dakota County, Hennepin County, and Ramsey County, which are all counties with populations larger than 40% the target population for a district.

Validation

validation_20220622_0919

SMC: 5,000 sampled plans of 8 districts on 4,110 units
`adapt_k_thresh`=0.985 • `seq_alpha`=0.5
`est_label_mult`=1 • `pop_temper`=0

Plan diversity 80% range: 0.78 to 0.98

R-hat values for summary statistics:
   pop_overlap      total_vap       plan_dev      comp_edge    comp_polsby       pop_hisp      pop_white      pop_black       pop_aian 
     1.0021156      1.0032955      1.0003563      1.0028069      1.0001263      1.0028537      1.0001096      1.0092273      1.0045958 
     pop_asian       pop_nhpi      pop_other        pop_two       vap_hisp      vap_white      vap_black       vap_aian      vap_asian 
     1.0095851      1.0082475      1.0028286      1.0055245      1.0021447      1.0020708      1.0081246      1.0048890      1.0129463 
      vap_nhpi      vap_other        vap_two pre_16_rep_tru pre_16_dem_cli uss_18_rep_new uss_18_dem_klo gov_18_rep_joh gov_18_dem_wal 
     1.0052569      1.0023381      1.0017581      1.0014413      1.0012044      1.0005152      1.0032816      1.0058428      1.0000147 
atg_18_rep_war atg_18_dem_ell sos_18_rep_how sos_18_dem_sim pre_20_dem_bid pre_20_rep_tru uss_20_dem_smi uss_20_rep_lew         arv_16 
     1.0015605      1.0008013      1.0017057      1.0012099      1.0103774      0.9998522      1.0093666      1.0009221      1.0014413 
        adv_16         arv_18         adv_18         arv_20         adv_20  county_splits    muni_splits            ndv            nrv 
     1.0012044      1.0023098      1.0002515      1.0000633      1.0107234      1.0003528      1.0034483      1.0072824      1.0002683 
       ndshare          e_dvs         pr_dem          e_dem          pbias           egap 
     0.9999162      0.9999111      1.0001969      1.0008631      1.0066382      1.0004667 

Sampling diagnostics for SMC run 1 of 2 (2,500 samples)
         Eff. samples (%) Acc. rate Log wgt. sd  Max. unique Est. k 
Split 1     2,455 (98.2%)     15.1%        0.27 1,577 (100%)     17 
Split 2     2,417 (96.7%)     21.6%        0.34 1,567 ( 99%)     10 
Split 3     2,387 (95.5%)     28.9%        0.43 1,609 (102%)      6 
Split 4     2,341 (93.7%)     33.4%        0.51 1,573 (100%)      4 
Split 5     2,287 (91.5%)     35.9%        0.55 1,537 ( 97%)      3 
Split 6     2,297 (91.9%)     35.6%        0.53 1,476 ( 93%)      2 
Split 7     2,304 (92.1%)     12.9%        0.55 1,325 ( 84%)      2 
Resample    1,749 (70.0%)       NA%        0.54 1,449 ( 92%)     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     2,457 (98.3%)     14.6%        0.26 1,596 (101%)     17 
Split 2     2,408 (96.3%)     21.5%        0.35 1,567 ( 99%)     10 
Split 3     2,379 (95.1%)     27.6%        0.44 1,546 ( 98%)      6 
Split 4     2,340 (93.6%)     33.4%        0.51 1,532 ( 97%)      4 
Split 5     2,341 (93.6%)     25.9%        0.52 1,539 ( 97%)      5 
Split 6     2,297 (91.9%)     29.6%        0.55 1,508 ( 95%)      3 
Split 7     2,302 (92.1%)     13.1%        0.55 1,317 ( 83%)      2 
Resample    1,749 (70.0%)       NA%        0.55 1,444 ( 91%)     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 master 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

alarm-redist / fifty-states