{
  "alt": "Dot chart with two panels, vote-weighted and county-equal, and one row for each of five axes, showing for 2024 the coefficient of each axis alone, with the four others held fixed, and with the four others and state baselines. Vote-weighted, college share is {fact:r_edu_2024_w} alone and {fact:b_edu_2024_w} with the others held fixed, rural share goes from {fact:r_rural_2024_w} to {fact:b_rural_2024_w}, income from {fact:r_inc_2024_w} to {fact:b_inc_2024_w}, and median age from {fact:r_age_2024_w} to {fact:b_age_2024_w}. A second view shows 2000.",
  "caption": "Vote-weighted, college share has the largest coefficient when the axes are held together, in {fact:jfirst_edu_2024_w} of resamples of states, while rural share's coefficient drops to {fact:b_rural_2024_w} and median age's to {fact:b_age_2024_w}. Each dot is a coefficient from a regression of the standardized margin on standardized axes; a coefficient of one axis alone equals its correlation. Intervals are 95% intervals with errors clustered by state. State baselines give each state its own average margin, so the coefficients compare counties within a state.",
  "data": [
    {
      "axis": "Education",
      "conf_high": 0.722,
      "conf_low": 0.604,
      "estimate": 0.663,
      "model": "Each axis alone",
      "n_units": 3103,
      "weighting": "Vote-weighted",
      "year": 2024
    },
    {
      "axis": "Education",
      "conf_high": 0.381,
      "conf_low": 0.182,
      "estimate": 0.282,
      "model": "Each axis alone",
      "n_units": 3113,
      "weighting": "Vote-weighted",
      "year": 2000
    },
    {
      "axis": "Income",
      "conf_high": 0.504,
      "conf_low": 0.29,
      "estimate": 0.397,
      "model": "Each axis alone",
      "n_units": 3103,
      "weighting": "Vote-weighted",
      "year": 2024
    },
    {
      "axis": "Income",
      "conf_high": 0.198,
      "conf_low": -0.005,
      "estimate": 0.096,
      "model": "Each axis alone",
      "n_units": 3113,
      "weighting": "Vote-weighted",
      "year": 2000
    },
    {
      "axis": "Race and ethnicity",
      "conf_high": -0.44,
      "conf_low": -0.707,
      "estimate": -0.574,
      "model": "Each axis alone",
      "n_units": 3103,
      "weighting": "Vote-weighted",
      "year": 2024
    },
    {
      "axis": "Race and ethnicity",
      "conf_high": -0.357,
      "conf_low": -0.681,
      "estimate": -0.519,
      "model": "Each axis alone",
      "n_units": 3113,
      "weighting": "Vote-weighted",
      "year": 2000
    },
    {
      "axis": "Age",
      "conf_high": -0.214,
      "conf_low": -0.406,
      "estimate": -0.31,
      "model": "Each axis alone",
      "n_units": 3103,
      "weighting": "Vote-weighted",
      "year": 2024
    },
    {
      "axis": "Age",
      "conf_high": 0.036,
      "conf_low": -0.187,
      "estimate": -0.076,
      "model": "Each axis alone",
      "n_units": 3113,
      "weighting": "Vote-weighted",
      "year": 2000
    },
    {
      "axis": "Rurality",
      "conf_high": -0.564,
      "conf_low": -0.741,
      "estimate": -0.653,
      "model": "Each axis alone",
      "n_units": 3103,
      "weighting": "Vote-weighted",
      "year": 2024
    },
    {
      "axis": "Rurality",
      "conf_high": -0.357,
      "conf_low": -0.565,
      "estimate": -0.461,
      "model": "Each axis alone",
      "n_units": 3113,
      "weighting": "Vote-weighted",
      "year": 2000
    },
    {
      "axis": "Education",
      "conf_high": 0.638,
      "conf_low": 0.474,
      "estimate": 0.556,
      "model": "Each axis alone",
      "n_units": 3103,
      "weighting": "County-equal",
      "year": 2024
    },
    {
      "axis": "Education",
      "conf_high": 0.195,
      "conf_low": 0.005,
      "estimate": 0.1,
      "model": "Each axis alone",
      "n_units": 3113,
      "weighting": "County-equal",
      "year": 2000
    },
    {
      "axis": "Income",
      "conf_high": 0.434,
      "conf_low": 0.173,
      "estimate": 0.304,
      "model": "Each axis alone",
      "n_units": 3103,
      "weighting": "County-equal",
      "year": 2024
    },
    {
      "axis": "Income",
      "conf_high": 0.137,
      "conf_low": -0.101,
      "estimate": 0.018,
      "model": "Each axis alone",
      "n_units": 3113,
      "weighting": "County-equal",
      "year": 2000
    },
    {
      "axis": "Race and ethnicity",
      "conf_high": -0.285,
      "conf_low": -0.707,
      "estimate": -0.496,
      "model": "Each axis alone",
      "n_units": 3103,
      "weighting": "County-equal",
      "year": 2024
    },
    {
      "axis": "Race and ethnicity",
      "conf_high": -0.259,
      "conf_low": -0.541,
      "estimate": -0.4,
      "model": "Each axis alone",
      "n_units": 3113,
      "weighting": "County-equal",
      "year": 2000
    },
    {
      "axis": "Age",
      "conf_high": -0.118,
      "conf_low": -0.272,
      "estimate": -0.195,
      "model": "Each axis alone",
      "n_units": 3103,
      "weighting": "County-equal",
      "year": 2024
    },
    {
      "axis": "Age",
      "conf_high": -0.054,
      "conf_low": -0.283,
      "estimate": -0.169,
      "model": "Each axis alone",
      "n_units": 3113,
      "weighting": "County-equal",
      "year": 2000
    },
    {
      "axis": "Rurality",
      "conf_high": -0.462,
      "conf_low": -0.592,
      "estimate": -0.527,
      "model": "Each axis alone",
      "n_units": 3103,
      "weighting": "County-equal",
      "year": 2024
    },
    {
      "axis": "Rurality",
      "conf_high": -0.18,
      "conf_low": -0.357,
      "estimate": -0.269,
      "model": "Each axis alone",
      "n_units": 3113,
      "weighting": "County-equal",
      "year": 2000
    },
    {
      "axis": "Education",
      "conf_high": 0.795,
      "conf_low": 0.63,
      "estimate": 0.712,
      "model": "All five together",
      "n_units": 3103,
      "weighting": "Vote-weighted",
      "year": 2024
    },
    {
      "axis": "Education",
      "conf_high": 0.394,
      "conf_low": 0.112,
      "estimate": 0.253,
      "model": "All five together",
      "n_units": 3113,
      "weighting": "Vote-weighted",
      "year": 2000
    },
    {
      "axis": "Income",
      "conf_high": -0.109,
      "conf_low": -0.402,
      "estimate": -0.255,
      "model": "All five together",
      "n_units": 3103,
      "weighting": "Vote-weighted",
      "year": 2024
    },
    {
      "axis": "Income",
      "conf_high": -0.06,
      "conf_low": -0.277,
      "estimate": -0.169,
      "model": "All five together",
      "n_units": 3113,
      "weighting": "Vote-weighted",
      "year": 2000
    },
    {
      "axis": "Race and ethnicity",
      "conf_high": -0.291,
      "conf_low": -0.569,
      "estimate": -0.43,
      "model": "All five together",
      "n_units": 3103,
      "weighting": "Vote-weighted",
      "year": 2024
    },
    {
      "axis": "Race and ethnicity",
      "conf_high": -0.353,
      "conf_low": -0.655,
      "estimate": -0.504,
      "model": "All five together",
      "n_units": 3113,
      "weighting": "Vote-weighted",
      "year": 2000
    },
    {
      "axis": "Age",
      "conf_high": 0.209,
      "conf_low": -0.133,
      "estimate": 0.038,
      "model": "All five together",
      "n_units": 3103,
      "weighting": "Vote-weighted",
      "year": 2024
    },
    {
      "axis": "Age",
      "conf_high": 0.486,
      "conf_low": 0.102,
      "estimate": 0.294,
      "model": "All five together",
      "n_units": 3113,
      "weighting": "Vote-weighted",
      "year": 2000
    },
    {
      "axis": "Rurality",
      "conf_high": 0.007,
      "conf_low": -0.251,
      "estimate": -0.122,
      "model": "All five together",
      "n_units": 3103,
      "weighting": "Vote-weighted",
      "year": 2024
    },
    {
      "axis": "Rurality",
      "conf_high": -0.114,
      "conf_low": -0.379,
      "estimate": -0.246,
      "model": "All five together",
      "n_units": 3113,
      "weighting": "Vote-weighted",
      "year": 2000
    },
    {
      "axis": "Education",
      "conf_high": 0.64,
      "conf_low": 0.482,
      "estimate": 0.561,
      "model": "All five together",
      "n_units": 3103,
      "weighting": "County-equal",
      "year": 2024
    },
    {
      "axis": "Education",
      "conf_high": 0.142,
      "conf_low": -0.092,
      "estimate": 0.025,
      "model": "All five together",
      "n_units": 3113,
      "weighting": "County-equal",
      "year": 2000
    },
    {
      "axis": "Income",
      "conf_high": -0.056,
      "conf_low": -0.226,
      "estimate": -0.141,
      "model": "All five together",
      "n_units": 3103,
      "weighting": "County-equal",
      "year": 2024
    },
    {
      "axis": "Income",
      "conf_high": 0.099,
      "conf_low": -0.12,
      "estimate": -0.011,
      "model": "All five together",
      "n_units": 3113,
      "weighting": "County-equal",
      "year": 2000
    },
    {
      "axis": "Race and ethnicity",
      "conf_high": -0.284,
      "conf_low": -0.665,
      "estimate": -0.475,
      "model": "All five together",
      "n_units": 3103,
      "weighting": "County-equal",
      "year": 2024
    },
    {
      "axis": "Race and ethnicity",
      "conf_high": -0.223,
      "conf_low": -0.551,
      "estimate": -0.387,
      "model": "All five together",
      "n_units": 3113,
      "weighting": "County-equal",
      "year": 2000
    },
    {
      "axis": "Age",
      "conf_high": 0.202,
      "conf_low": 0.066,
      "estimate": 0.134,
      "model": "All five together",
      "n_units": 3103,
      "weighting": "County-equal",
      "year": 2024
    },
    {
      "axis": "Age",
      "conf_high": 0.2,
      "conf_low": -0.02,
      "estimate": 0.09,
      "model": "All five together",
      "n_units": 3113,
      "weighting": "County-equal",
      "year": 2000
    },
    {
      "axis": "Rurality",
      "conf_high": -0.105,
      "conf_low": -0.305,
      "estimate": -0.205,
      "model": "All five together",
      "n_units": 3103,
      "weighting": "County-equal",
      "year": 2024
    },
    {
      "axis": "Rurality",
      "conf_high": -0.123,
      "conf_low": -0.282,
      "estimate": -0.202,
      "model": "All five together",
      "n_units": 3113,
      "weighting": "County-equal",
      "year": 2000
    },
    {
      "axis": "Education",
      "conf_high": 0.803,
      "conf_low": 0.654,
      "estimate": 0.729,
      "model": "All five with state baselines",
      "n_units": 3103,
      "weighting": "Vote-weighted",
      "year": 2024
    },
    {
      "axis": "Education",
      "conf_high": 0.384,
      "conf_low": 0.142,
      "estimate": 0.263,
      "model": "All five with state baselines",
      "n_units": 3113,
      "weighting": "Vote-weighted",
      "year": 2000
    },
    {
      "axis": "Income",
      "conf_high": -0.331,
      "conf_low": -0.478,
      "estimate": -0.405,
      "model": "All five with state baselines",
      "n_units": 3103,
      "weighting": "Vote-weighted",
      "year": 2024
    },
    {
      "axis": "Income",
      "conf_high": -0.175,
      "conf_low": -0.324,
      "estimate": -0.249,
      "model": "All five with state baselines",
      "n_units": 3113,
      "weighting": "Vote-weighted",
      "year": 2000
    },
    {
      "axis": "Race and ethnicity",
      "conf_high": -0.479,
      "conf_low": -0.764,
      "estimate": -0.621,
      "model": "All five with state baselines",
      "n_units": 3103,
      "weighting": "Vote-weighted",
      "year": 2024
    },
    {
      "axis": "Race and ethnicity",
      "conf_high": -0.638,
      "conf_low": -0.904,
      "estimate": -0.771,
      "model": "All five with state baselines",
      "n_units": 3113,
      "weighting": "Vote-weighted",
      "year": 2000
    },
    {
      "axis": "Age",
      "conf_high": 0.135,
      "conf_low": 0.016,
      "estimate": 0.076,
      "model": "All five with state baselines",
      "n_units": 3103,
      "weighting": "Vote-weighted",
      "year": 2024
    },
    {
      "axis": "Age",
      "conf_high": 0.33,
      "conf_low": 0.106,
      "estimate": 0.218,
      "model": "All five with state baselines",
      "n_units": 3113,
      "weighting": "Vote-weighted",
      "year": 2000
    },
    {
      "axis": "Rurality",
      "conf_high": -0.035,
      "conf_low": -0.145,
      "estimate": -0.09,
      "model": "All five with state baselines",
      "n_units": 3103,
      "weighting": "Vote-weighted",
      "year": 2024
    },
    {
      "axis": "Rurality",
      "conf_high": -0.007,
      "conf_low": -0.189,
      "estimate": -0.098,
      "model": "All five with state baselines",
      "n_units": 3113,
      "weighting": "Vote-weighted",
      "year": 2000
    },
    {
      "axis": "Education",
      "conf_high": 0.6,
      "conf_low": 0.475,
      "estimate": 0.537,
      "model": "All five with state baselines",
      "n_units": 3103,
      "weighting": "County-equal",
      "year": 2024
    },
    {
      "axis": "Education",
      "conf_high": 0.243,
      "conf_low": 0.064,
      "estimate": 0.153,
      "model": "All five with state baselines",
      "n_units": 3113,
      "weighting": "County-equal",
      "year": 2000
    },
    {
      "axis": "Income",
      "conf_high": -0.125,
      "conf_low": -0.226,
      "estimate": -0.176,
      "model": "All five with state baselines",
      "n_units": 3103,
      "weighting": "County-equal",
      "year": 2024
    },
    {
      "axis": "Income",
      "conf_high": -0.078,
      "conf_low": -0.227,
      "estimate": -0.152,
      "model": "All five with state baselines",
      "n_units": 3113,
      "weighting": "County-equal",
      "year": 2000
    },
    {
      "axis": "Race and ethnicity",
      "conf_high": -0.614,
      "conf_low": -0.839,
      "estimate": -0.727,
      "model": "All five with state baselines",
      "n_units": 3103,
      "weighting": "County-equal",
      "year": 2024
    },
    {
      "axis": "Race and ethnicity",
      "conf_high": -0.596,
      "conf_low": -0.763,
      "estimate": -0.68,
      "model": "All five with state baselines",
      "n_units": 3113,
      "weighting": "County-equal",
      "year": 2000
    },
    {
      "axis": "Age",
      "conf_high": 0.152,
      "conf_low": 0.056,
      "estimate": 0.104,
      "model": "All five with state baselines",
      "n_units": 3103,
      "weighting": "County-equal",
      "year": 2024
    },
    {
      "axis": "Age",
      "conf_high": 0.175,
      "conf_low": 0.057,
      "estimate": 0.116,
      "model": "All five with state baselines",
      "n_units": 3113,
      "weighting": "County-equal",
      "year": 2000
    },
    {
      "axis": "Rurality",
      "conf_high": -0.06,
      "conf_low": -0.152,
      "estimate": -0.106,
      "model": "All five with state baselines",
      "n_units": 3103,
      "weighting": "County-equal",
      "year": 2024
    },
    {
      "axis": "Rurality",
      "conf_high": -0.05,
      "conf_low": -0.169,
      "estimate": -0.11,
      "model": "All five with state baselines",
      "n_units": 3113,
      "weighting": "County-equal",
      "year": 2000
    }
  ],
  "id": "rank_ladder",
  "notes": [
    "Election returns are full counts of votes, so they carry no sampling error. The 95% intervals use errors clustered by state, so they show how much a number depends on which states are in the set. They do not include the sampling error of the county characteristics, which are census and American Community Survey estimates interpolated between years.",
    "Standardization uses the weighted mean and standard deviation of the weighting shown, in the election shown."
  ],
  "source": "County presidential returns, 2000-2024 (Algara and Amlani for 2000 to 2020; MIT Election Data and Science Lab for 2024), full counts of votes; county characteristics from the decennial census and American Community Survey, interpolated to election years; estimates weighted by two-party votes or counting each county once, as stated",
  "spec": {
    "colors": {
      "All five together": "total",
      "All five with state baselines": "accent",
      "Each axis alone": "muted"
    },
    "facet": "weighting",
    "facetColumns": 2,
    "group": "model",
    "hi": "conf_high",
    "legend": true,
    "lo": "conf_low",
    "reference": 0,
    "sort": "data",
    "x": "estimate",
    "xDomain": [
      -1,
      1
    ],
    "xFormat": {
      "digits": 2,
      "signed": true
    },
    "xLabel": "Standardized coefficient (standard deviations of the margin per standard deviation of the axis)",
    "y": "axis"
  },
  "subtitle": "Standardized coefficients for the county two-party margin in 2024: each axis alone, all five axes together, and all five with a baseline for each state; two weightings",
  "table": {
    "columns": [
      {
        "format": {
          "digits": 0
        },
        "key": "year",
        "label": "Election"
      },
      {
        "key": "weighting",
        "label": "Weighting"
      },
      {
        "key": "axis",
        "label": "Axis"
      },
      {
        "key": "model",
        "label": "Model"
      },
      {
        "format": {
          "digits": 2,
          "signed": true
        },
        "key": "estimate",
        "label": "Coefficient"
      },
      {
        "format": {
          "digits": 2,
          "signed": true
        },
        "key": "conf_low",
        "label": "Interval low"
      },
      {
        "format": {
          "digits": 2,
          "signed": true
        },
        "key": "conf_high",
        "label": "Interval high"
      },
      {
        "format": {
          "thousands": true
        },
        "key": "n_units",
        "label": "Counties"
      }
    ]
  },
  "title": "Held together, college share's coefficient is {fact:b_edu_2024_w} against a correlation of {fact:r_edu_2024_w}, and income's is {fact:b_inc_2024_w} against {fact:r_inc_2024_w}, vote-weighted in 2024",
  "type": "dot",
  "views": [
    {
      "filter": {
        "year": 2024
      },
      "id": "y2024",
      "label": "2024"
    },
    {
      "caption": "Vote-weighted, the white share's coefficient with the other four axes held fixed is {fact:b_race_2000_w}, and with state baselines added it is {fact:bfe_race_2000_w}. Median age moves from a correlation of {fact:r_age_2000_w} to a coefficient of {fact:b_age_2000_w}. Each dot is a standardized coefficient with a 95% interval with errors clustered by state.",
      "filter": {
        "year": 2000
      },
      "id": "y2000",
      "label": "2000",
      "title": "In 2000 the white share has the largest coefficient with the other axes held fixed in {fact:jfirst_race_2000_w} of resamples, and median age's coefficient is {fact:b_age_2000_w} against a correlation of {fact:r_age_2000_w}"
    }
  ],
  "width": "wide"
}