{
  "alt": "Line chart of three series over five presidential elections from 2008 to 2024, each with a confidence band. The pooled gap runs from {fact:dc_2008_tot} points in 2008 to {fact:dc_2016_tot} in 2016 and {fact:dc_2024_tot} in 2024. The within-group part is {fact:dc_2008_win} in 2008, {fact:dc_2016_win} in 2016 and {fact:dc_2024_win} in 2024. The mix part is {fact:dc_2008_mix}, {fact:dc_2016_mix} and {fact:dc_2024_mix}.",
  "caption": "Each part is at least {fact:dc_min_part} points in every election, and the mix part is the larger in {fact:dc_n_mix_larger} of the five elections. The unaffiliated carry {fact:dcs_2024_una} of the 2024 within-group part, from a small weekly cell. The lines join the five presidential elections, and the bands are 95% intervals from a bootstrap of respondents.",
  "data": [
    {
      "conf_high": 27.245,
      "conf_low": 23.8642,
      "estimate": 25.5546,
      "n": 21124,
      "series": "Pooled gap",
      "year": 2008
    },
    {
      "conf_high": 12.8914,
      "conf_low": 8.42448,
      "estimate": 10.6579,
      "n": 21124,
      "series": "Gap inside groups",
      "year": 2008
    },
    {
      "conf_high": 16.7046,
      "conf_low": 13.0888,
      "estimate": 14.8967,
      "n": 21124,
      "series": "Mix of groups",
      "year": 2008
    },
    {
      "conf_high": 28.8204,
      "conf_low": 25.7083,
      "estimate": 27.2643,
      "n": 34338,
      "series": "Pooled gap",
      "year": 2012
    },
    {
      "conf_high": 17.2341,
      "conf_low": 12.6686,
      "estimate": 14.9514,
      "n": 34338,
      "series": "Gap inside groups",
      "year": 2012
    },
    {
      "conf_high": 14.1663,
      "conf_low": 10.4597,
      "estimate": 12.313,
      "n": 34338,
      "series": "Mix of groups",
      "year": 2012
    },
    {
      "conf_high": 20.4504,
      "conf_low": 17.4444,
      "estimate": 18.9474,
      "n": 37341,
      "series": "Pooled gap",
      "year": 2016
    },
    {
      "conf_high": 9.90352,
      "conf_low": 6.0693,
      "estimate": 7.98641,
      "n": 37341,
      "series": "Gap inside groups",
      "year": 2016
    },
    {
      "conf_high": 12.5058,
      "conf_low": 9.4161,
      "estimate": 10.961,
      "n": 37341,
      "series": "Mix of groups",
      "year": 2016
    },
    {
      "conf_high": 25.0028,
      "conf_low": 22.0718,
      "estimate": 23.5373,
      "n": 40502,
      "series": "Pooled gap",
      "year": 2020
    },
    {
      "conf_high": 10.6528,
      "conf_low": 6.74938,
      "estimate": 8.70107,
      "n": 40502,
      "series": "Gap inside groups",
      "year": 2020
    },
    {
      "conf_high": 16.3963,
      "conf_low": 13.2762,
      "estimate": 14.8362,
      "n": 40502,
      "series": "Mix of groups",
      "year": 2020
    },
    {
      "conf_high": 29.3532,
      "conf_low": 25.9807,
      "estimate": 27.6669,
      "n": 39039,
      "series": "Pooled gap",
      "year": 2024
    },
    {
      "conf_high": 17.4214,
      "conf_low": 11.7666,
      "estimate": 14.594,
      "n": 39039,
      "series": "Gap inside groups",
      "year": 2024
    },
    {
      "conf_high": 15.5419,
      "conf_low": 10.6039,
      "estimate": 13.0729,
      "n": 39039,
      "series": "Mix of groups",
      "year": 2024
    }
  ],
  "id": "gap_decomposition",
  "notes": [
    "The pooled gap here covers voters with a tradition-by-race group and an attendance answer in the frequent or seldom group, so it can differ by a few tenths of a point from the all-voter gap of the god-gap chapter. The within part weights each group's own gap by its average share of the two attendance groups, and the mix part prices the difference in the groups' shares at each group's average Democratic share; the two parts add to the pooled gap exactly.",
    "Standard errors come from {fact:boot_reps} seeded bootstrap resamples of respondents; the interval is a normal 95% interval around the estimate. The decomposition is an accounting of the gap and not a causal split.",
    "The unaffiliated contribute {fact:dcw_2024_una} of the {fact:dc_2024_win} points of the 2024 within-group part, and without them that part is {fact:dcx_2024_una} points. Their weekly cell has an effective sample of {fact:una_neff_2024} respondents in 2024 against {fact:una_neff_2012}, {fact:una_neff_2016} and {fact:una_neff_2020} in 2012, 2016 and 2020, and their gap of {fact:gpv_2024_una} points in 2024 compares with {fact:gpv_2012_una}, {fact:gpv_2016_una} and {fact:gpv_2020_una} in those elections."
  ],
  "source": "Cooperative Election Study, presidential years 2008, 2012, 2016, 2020 and 2024; weighted (weight_cumulative)",
  "spec": {
    "colors": {
      "Gap inside groups": "cat1",
      "Mix of groups": "cat2",
      "Pooled gap": "total"
    },
    "hi": "conf_high",
    "lo": "conf_low",
    "n": "n",
    "series": "series",
    "x": "year",
    "xDomain": [
      2008,
      2024
    ],
    "xLabel": "Presidential election year",
    "xTicks": "data",
    "y": "estimate",
    "yDomain": [
      0,
      40
    ],
    "yFormat": {
      "digits": 0
    },
    "yLabel": "Seldom minus frequent attenders (percentage points)"
  },
  "subtitle": "Seldom minus frequent attenders in the Democratic share of the two-party presidential vote, percentage points, split into a within-group part and a mix part, 2008 to 2024; 95% intervals",
  "table": {
    "columns": [
      {
        "key": "series",
        "label": "Part"
      },
      {
        "key": "year",
        "label": "Election"
      },
      {
        "format": {
          "digits": 1
        },
        "key": "estimate",
        "label": "Points"
      },
      {
        "format": {
          "digits": 1
        },
        "key": "conf_low",
        "label": "Lower"
      },
      {
        "format": {
          "digits": 1
        },
        "key": "conf_high",
        "label": "Upper"
      },
      {
        "format": {
          "thousands": true
        },
        "key": "n",
        "label": "Voters"
      }
    ]
  },
  "title": "Of the {fact:dc_2024_tot} point gap between seldom and frequent attenders in the 2024 vote, {fact:dc_2024_win} points is a gap inside tradition-by-race groups and {fact:dc_2024_mix} points reflects which groups the two attendance levels contain",
  "type": "line",
  "width": "wide"
}