{
  "alt": "Two tabs. The first is a scatter plot of the published ADI against the standardized percentile with a diagonal for equal ranks and two lines of binned means; the line for the lowest-cost counties lies above the line for the highest-cost counties in every tenth of the standardized ranking, and the gap widens from the least deprived tenth to the most deprived. The second is a table of tracts with poverty rates above the high-poverty threshold and published ADI percentiles near the least deprived end of the national ranking.",
  "caption": "At the same standardized percentile the binned means of the published ADI are higher in the lowest-cost counties than in the highest-cost counties in every tenth, and the 95% intervals of the two groups do not overlap. The two rankings correlate at {fact:rho_std_adi}, so the diagonal of equal percentiles is not a null for a binned mean, and the evidence is the gap between the groups. The first tab plots a seeded sample of {fact:n_sample} tracts with population-weighted binned means; the second lists the {fact:n_stark} tracts with a poverty rate of at least {fact:hp_threshold} and at least {fact:min_stark_pop} residents where the published percentile falls furthest below the standardized one, of which {fact:n_stark_nyc} are in New York City.",
  "data": [],
  "id": "adi_vs_standardized",
  "notes": [
    "Counties are grouped by their median home value into quartiles with equal numbers of residents; the middle two quartiles are drawn together in gray. Markers are population-weighted means of the published ADI within tenths of the standardized percentile for the lowest-cost and highest-cost groups, with 95% intervals from a bootstrap over counties; cells with few tracts are left out.",
    "The dots are a random sample of the frame's tracts drawn with a fixed seed (seed and share in the methods note); the means, intervals and the table use every tract.",
    "A tract's ACS medians rest on the homes and renters in the tract, which are few in some tracts, and the staged file has no margins of error; a college-town tract can show a high poverty rate because of student households. Each row illustrates what the formula does and is not an estimate of its tract's deprivation."
  ],
  "source": "Neighborhood Atlas ADI 2023; ACS 2019-2023; population-weighted (ACS tract population) binned means, modeled estimates",
  "spec": {
    "panels": [
      {
        "figure": {
          "alt": "Scatter plot with the standardized percentile on the horizontal axis and the published ADI on the vertical axis, with a diagonal. Two lines of binned means, one for the lowest-cost counties and one for the highest-cost counties, rise from left to right; the lowest-cost line lies above the highest-cost line in every tenth of the standardized ranking and the gap between them widens.",
          "caption": "The line of binned means for the lowest-cost counties lies above the line for the highest-cost counties in every tenth of the standardized ranking, and the gap widens toward the most deprived tenth.",
          "data": [],
          "id": "adi_scatter",
          "spec": {
            "colors": {
              "Highest-cost counties": "highlight",
              "Lowest-cost counties": "cat1",
              "Middle-cost counties": "muted"
            },
            "group": "group",
            "identity": true,
            "identityLabel": "Equal percentile",
            "overlays": [
              {
                "hi": "hi",
                "kind": "line",
                "label": "Lowest-cost counties, binned means",
                "lo": "lo",
                "rows": [
                  {
                    "hi": 31.66,
                    "lo": 27.4,
                    "n_units": 149,
                    "x": 6.75,
                    "y": 29.22
                  },
                  {
                    "hi": 42.01,
                    "lo": 39.55,
                    "n_units": 467,
                    "x": 15.92,
                    "y": 40.73
                  },
                  {
                    "hi": 52.25,
                    "lo": 50.75,
                    "n_units": 985,
                    "x": 25.6,
                    "y": 51.48
                  },
                  {
                    "hi": 59.82,
                    "lo": 58.43,
                    "n_units": 1524,
                    "x": 35.29,
                    "y": 59.11
                  },
                  {
                    "hi": 66.77,
                    "lo": 65.61,
                    "n_units": 2304,
                    "x": 45.27,
                    "y": 66.19
                  },
                  {
                    "hi": 71.89,
                    "lo": 70.85,
                    "n_units": 2855,
                    "x": 55.14,
                    "y": 71.37
                  },
                  {
                    "hi": 77.23,
                    "lo": 76.26,
                    "n_units": 3283,
                    "x": 65.12,
                    "y": 76.73
                  },
                  {
                    "hi": 81.78,
                    "lo": 80.89,
                    "n_units": 3546,
                    "x": 75.01,
                    "y": 81.33
                  },
                  {
                    "hi": 86.64,
                    "lo": 85.76,
                    "n_units": 3460,
                    "x": 84.9,
                    "y": 86.21
                  },
                  {
                    "hi": 93.28,
                    "lo": 92.31,
                    "n_units": 3450,
                    "x": 94.95,
                    "y": 92.8
                  }
                ],
                "x": "x",
                "y": "y"
              },
              {
                "hi": "hi",
                "kind": "line",
                "label": "Highest-cost counties, binned means",
                "lo": "lo",
                "rows": [
                  {
                    "hi": 8.93,
                    "lo": 6.55,
                    "n_units": 4514,
                    "x": 4.43,
                    "y": 7.58
                  },
                  {
                    "hi": 16.13,
                    "lo": 12.86,
                    "n_units": 2839,
                    "x": 14.71,
                    "y": 14.37
                  },
                  {
                    "hi": 20.44,
                    "lo": 16.82,
                    "n_units": 2058,
                    "x": 24.69,
                    "y": 18.56
                  },
                  {
                    "hi": 23.56,
                    "lo": 19.37,
                    "n_units": 1586,
                    "x": 34.85,
                    "y": 21.36
                  },
                  {
                    "hi": 26.44,
                    "lo": 20.96,
                    "n_units": 1240,
                    "x": 44.79,
                    "y": 23.5
                  },
                  {
                    "hi": 28.65,
                    "lo": 21.63,
                    "n_units": 1155,
                    "x": 54.9,
                    "y": 24.77
                  },
                  {
                    "hi": 30.65,
                    "lo": 22.89,
                    "n_units": 1057,
                    "x": 64.94,
                    "y": 26.17
                  },
                  {
                    "hi": 33.65,
                    "lo": 24,
                    "n_units": 1080,
                    "x": 75.04,
                    "y": 27.93
                  },
                  {
                    "hi": 36.69,
                    "lo": 25.98,
                    "n_units": 1102,
                    "x": 85.01,
                    "y": 30.42
                  },
                  {
                    "hi": 40.63,
                    "lo": 26.68,
                    "n_units": 1007,
                    "x": 94.44,
                    "y": 31.89
                  }
                ],
                "x": "x",
                "y": "y"
              }
            ],
            "payload": "adi_vs_standardized.json",
            "x": "std",
            "xDomain": [
              0,
              100
            ],
            "xFormat": {
              "digits": 0
            },
            "xLabel": "Standardized replica score, percentile among tracts (higher is more deprived)",
            "y": "adi",
            "yDomain": [
              0,
              100
            ],
            "yFormat": {
              "digits": 0
            },
            "yLabel": "Published ADI, national percentile (higher is more deprived)"
          },
          "subtitle": "Published ADI against the standardized percentile, one dot per sampled tract, colored by the median home value of the tract's county",
          "title": "At the same standardized percentile, tracts in the highest-cost counties have a lower published ADI than tracts in the lowest-cost counties",
          "type": "scatter"
        },
        "label": "Tracts"
      },
      {
        "figure": {
          "alt": "Table of tracts, one row each, with the county, residents, poverty rate, median home value, published ADI and standardized percentile, sorted from the largest gap down.",
          "caption": "Each row is a tract with poverty above the high-poverty threshold and a published ADI near the least deprived end of the ranking, with a standardized percentile near the most deprived end.",
          "data": [
            {
              "adi": 1,
              "home_value": 2000001,
              "place": "San Francisco, CA",
              "poverty": 35.9,
              "residents": 1814,
              "standardized": 99.7
            },
            {
              "adi": 2,
              "home_value": 1767400,
              "place": "Kings, NY",
              "poverty": 41.2,
              "residents": 5261,
              "standardized": 98.1
            },
            {
              "adi": 3,
              "home_value": 1316700,
              "place": "Kings, NY",
              "poverty": 43.6,
              "residents": 10085,
              "standardized": 98.7
            },
            {
              "adi": 6,
              "home_value": 1010000,
              "place": "Kings, NY",
              "poverty": 48.4,
              "residents": 1861,
              "standardized": 99.8
            },
            {
              "adi": 6,
              "home_value": 1137500,
              "place": "Los Angeles, CA",
              "poverty": 35.9,
              "residents": 2168,
              "standardized": 99.7
            },
            {
              "adi": 1,
              "home_value": 2000001,
              "place": "New York, NY",
              "poverty": 32,
              "residents": 4755,
              "standardized": 94.3
            },
            {
              "adi": 7,
              "home_value": 1044300,
              "place": "Bronx, NY",
              "poverty": 46.4,
              "residents": 5460,
              "standardized": 98.7
            },
            {
              "adi": 6,
              "home_value": 1032300,
              "place": "Queens, NY",
              "poverty": 35.5,
              "residents": 3004,
              "standardized": 97.6
            },
            {
              "adi": 5,
              "home_value": 1138600,
              "place": "Kings, NY",
              "poverty": 45.1,
              "residents": 4887,
              "standardized": 96.6
            },
            {
              "adi": 5,
              "home_value": 1133500,
              "place": "Kings, NY",
              "poverty": 33,
              "residents": 3344,
              "standardized": 96.3
            },
            {
              "adi": 5,
              "home_value": 1179700,
              "place": "Kings, NY",
              "poverty": 31.8,
              "residents": 2902,
              "standardized": 95.9
            },
            {
              "adi": 3,
              "home_value": 1350500,
              "place": "Kings, NY",
              "poverty": 49.3,
              "residents": 4270,
              "standardized": 93.8
            },
            {
              "adi": 1,
              "home_value": 2000001,
              "place": "Madison, ID",
              "poverty": 63.3,
              "residents": 12195,
              "standardized": 91.6
            },
            {
              "adi": 3,
              "home_value": 1308300,
              "place": "Kings, NY",
              "poverty": 30.9,
              "residents": 4085,
              "standardized": 93.6
            },
            {
              "adi": 4,
              "home_value": 1311400,
              "place": "New York, NY",
              "poverty": 36.7,
              "residents": 10179,
              "standardized": 94.5
            }
          ],
          "id": "adi_gaps",
          "spec": {
            "columns": [
              {
                "key": "place",
                "label": "County"
              },
              {
                "format": {
                  "digits": 0,
                  "thousands": true
                },
                "key": "residents",
                "label": "Residents"
              },
              {
                "format": {
                  "digits": 1
                },
                "key": "poverty",
                "label": "Poverty rate (%)"
              },
              {
                "format": {
                  "digits": 0,
                  "thousands": true
                },
                "key": "home_value",
                "label": "Median home value ($)"
              },
              {
                "format": {
                  "digits": 0
                },
                "key": "adi",
                "label": "Published ADI (percentile)"
              },
              {
                "format": {
                  "digits": 1
                },
                "key": "standardized",
                "label": "Standardized score (percentile)"
              }
            ]
          },
          "subtitle": "Tracts with a high poverty rate where the published ADI percentile is furthest below the standardized percentile",
          "title": "{fact:n_stark_nyc} of the {fact:n_stark} tracts with the largest gaps are in New York City",
          "type": "table"
        },
        "label": "Largest gaps"
      }
    ]
  },
  "subtitle": "Tract percentile on the published ADI against the percentile of the standardized replica score, by the cost of the tract's county, and the tracts with the largest gaps",
  "title": "The published ADI percentile minus the standardized percentile averages {fact:disp_q4} in the highest-cost counties and {fact:disp_q1} in the lowest-cost counties",
  "type": "tabs",
  "width": "wide"
}