2010 Iowa Congressional Districts

[philipwosull]

Redistricting requirements

In Iowa, districts must:

1. be contiguous
2. have equal populations
3. be geographically compact with compactness defined as length-width compactness and perimeter compactness
4. not split counties
5. preserve municipality boundaries as much as possible

Algorithmic Constraints

We enforce a maximum population deviation of 0.01%.

Data Sources

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

Pre-processing Notes

Shape file was grouped by county to prevent county splits.

Simulation Notes

We sample 5,000 districting plans for Iowa. No special techniques were needed to produce the sample.

Validation

SMC: 5,000 sampled plans of 4 districts on 99 units
`adapt_k_thresh`=0.985 • `seq_alpha`=0.9
`est_label_mult`=1 • `pop_temper`=0

Plan diversity 80% range: 0.00 to 0.79

R-hat values for summary statistics:
   pop_overlap      total_vap       plan_dev      comp_edge    comp_polsby      pop_white      pop_black       pop_hisp       pop_aian 
      1.031659       1.032497       1.046306       1.019521       1.014219       1.067511       1.010439       1.038040       1.049245 
     pop_asian       pop_nhpi      pop_other        pop_two      vap_white      vap_black       vap_hisp       vap_aian      vap_asian 
      1.068630       1.065857       1.047719       1.022109       1.034628       1.009227       1.041492       1.048448       1.071513 
      vap_nhpi      vap_other        vap_two pre_16_rep_tru pre_16_dem_cli pre_20_rep_tru pre_20_dem_bid uss_16_rep_gra uss_16_dem_jud 
      1.063447       1.049689       1.060552       1.025999       1.012453       1.047613       1.012420       1.013083       1.010033 
uss_20_rep_ern uss_20_dem_gre gov_18_rep_rey gov_18_dem_hub atg_18_dem_mil sos_18_rep_pat sos_18_dem_dej         adv_16         adv_18 
      1.050681       1.010924       1.020413       1.035063       1.016983       1.015582       1.019597       1.011215       1.012726 
        adv_20         arv_16         arv_18         arv_20            ndv            nrv        ndshare        comp_lw           area 
      1.011222       1.013956       1.019411       1.049174       1.011783       1.025499       1.029347       1.038156       1.017200 
    comp_perim          e_dvs         pr_dem          e_dem          pbias           egap 
      1.008834       1.024968       1.014725       1.020896       1.006218       1.016010 
✖ WARNING: SMC runs have not converged.

Sampling diagnostics for SMC run 1 of 4 (4,000 samples)
         Eff. samples (%) Acc. rate Log wgt. sd  Max. unique Est. k 
Split 1     2,120 (53.0%)      0.3%        1.41 2,547 (101%)      1 
Split 2       866 (21.6%)      0.2%        0.86 1,830 ( 72%)      1 
Split 3       619 (15.5%)      0.0%        0.94   769 ( 30%)      1 
Resample      444 (11.1%)       NA%        0.90 1,943 ( 77%)     NA 

Sampling diagnostics for SMC run 2 of 4 (4,000 samples)
         Eff. samples (%) Acc. rate Log wgt. sd  Max. unique Est. k 
Split 1     2,112 (52.8%)      0.1%        1.42 2,541 (100%)      3 
Split 2       934 (23.4%)      0.1%        0.81 1,781 ( 70%)      2 
Split 3     2,034 (50.8%)      0.0%        0.59   621 ( 25%)      2 
Resample    1,629 (40.7%)       NA%        0.57 3,017 (119%)     NA 

Sampling diagnostics for SMC run 3 of 4 (4,000 samples)
         Eff. samples (%) Acc. rate Log wgt. sd  Max. unique Est. k 
Split 1     2,145 (53.6%)      0.1%        1.42 2,515 ( 99%)      3 
Split 2     1,070 (26.7%)      0.1%        0.79 1,831 ( 72%)      2 
Split 3     2,147 (53.7%)      0.0%        0.77   893 ( 35%)      2 
Resample    1,839 (46.0%)       NA%        0.75 2,678 (106%)     NA 

Sampling diagnostics for SMC run 4 of 4 (4,000 samples)
         Eff. samples (%) Acc. rate Log wgt. sd  Max. unique Est. k 
Split 1     2,173 (54.3%)      0.1%        1.44 2,508 ( 99%)      3 
Split 2       838 (20.9%)      0.1%        0.90 1,789 ( 71%)      2 
Split 3     2,002 (50.0%)      0.0%        0.62   906 ( 36%)      2 
Resample    1,509 (37.7%)       NA%        0.59 3,060 (121%)     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.

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

[CoryMcCartan]

Looks great! Can you re-run summary(plans) on the plans object with all the summary stats calculated? that will show us R-hat values for all the stats so we can double-check

[philipwosull]

Updated PR @CoryMcCartan

[philipwosull]

Formatting updated @CoryMcCartan

[CoryMcCartan]

Awesome, thank you!