{
  "alt": "A dot-and-interval chart in two panels, health insurance and government services, each with one row for every year and mode. The health-insurance correlation among face-to-face respondents is {fact:hl_ftf_2008} in 2008, {fact:hl_ftf_2012} in 2012, {fact:hl_ftf_2016} in 2016 and {fact:hl_ftf_2024} in 2024, and among web respondents {fact:hl_web_2012}, {fact:hl_web_2016} and {fact:hl_web_2024}. The government-services correlation is {fact:sv_ftf_2008}, {fact:sv_ftf_2012}, {fact:sv_ftf_2016} and {fact:sv_ftf_2024} face-to-face, and {fact:sv_web_2012}, {fact:sv_web_2016} and {fact:sv_web_2024} on the web.",
  "caption": "In 2012 the web dot lies right of the face-to-face dot in both panels and the intervals do not overlap. ANES interviewed face to face only in 2008, so the 2008 to 2012 change among face-to-face respondents is {fact:hl_ftf_chg_0812} for health insurance and {fact:sv_ftf_chg_0812} for government services, against {fact:hl_chg_0812} and {fact:sv_chg_0812} among all respondents. Each dot is a weighted correlation with its own mode weight, and each line is a 95% interval.",
  "data": [
    {
      "conf_high": 0.306429,
      "conf_low": 0.115345,
      "estimate": 0.212922,
      "mode": "Face-to-face",
      "n": 476,
      "n_eff": 384,
      "outcome": "Health insurance",
      "row": "2008, face-to-face",
      "year": 2008
    },
    {
      "conf_high": 0.351046,
      "conf_low": 0.199759,
      "estimate": 0.277119,
      "mode": "Face-to-face",
      "n": 801,
      "n_eff": 573,
      "outcome": "Health insurance",
      "row": "2012, face-to-face",
      "year": 2012
    },
    {
      "conf_high": 0.457478,
      "conf_low": 0.372902,
      "estimate": 0.41609,
      "mode": "Web",
      "n": 2319,
      "n_eff": 1470,
      "outcome": "Health insurance",
      "row": "2012, web",
      "year": 2012
    },
    {
      "conf_high": 0.541435,
      "conf_low": 0.395275,
      "estimate": 0.471588,
      "mode": "Face-to-face",
      "n": 671,
      "n_eff": 437,
      "outcome": "Health insurance",
      "row": "2016, face-to-face",
      "year": 2016
    },
    {
      "conf_high": 0.471557,
      "conf_low": 0.38093,
      "estimate": 0.427316,
      "mode": "Web",
      "n": 1709,
      "n_eff": 1252,
      "outcome": "Health insurance",
      "row": "2016, web",
      "year": 2016
    },
    {
      "conf_high": 0.58447,
      "conf_low": 0.420184,
      "estimate": 0.506916,
      "mode": "Face-to-face",
      "n": 591,
      "n_eff": 317,
      "outcome": "Health insurance",
      "row": "2024, face-to-face",
      "year": 2024
    },
    {
      "conf_high": 0.526524,
      "conf_low": 0.408923,
      "estimate": 0.469805,
      "mode": "Web",
      "n": 1120,
      "n_eff": 677,
      "outcome": "Health insurance",
      "row": "2024, web",
      "year": 2024
    },
    {
      "conf_high": 0.226483,
      "conf_low": 0.0246198,
      "estimate": 0.126864,
      "mode": "Face-to-face",
      "n": 450,
      "n_eff": 366,
      "outcome": "Government services",
      "row": "2008, face-to-face",
      "year": 2008
    },
    {
      "conf_high": 0.336366,
      "conf_low": 0.178803,
      "estimate": 0.259309,
      "mode": "Face-to-face",
      "n": 755,
      "n_eff": 539,
      "outcome": "Government services",
      "row": "2012, face-to-face",
      "year": 2012
    },
    {
      "conf_high": 0.438555,
      "conf_low": 0.351463,
      "estimate": 0.395899,
      "mode": "Web",
      "n": 2272,
      "n_eff": 1442,
      "outcome": "Government services",
      "row": "2012, web",
      "year": 2012
    },
    {
      "conf_high": 0.507287,
      "conf_low": 0.34946,
      "estimate": 0.431671,
      "mode": "Face-to-face",
      "n": 631,
      "n_eff": 410,
      "outcome": "Government services",
      "row": "2016, face-to-face",
      "year": 2016
    },
    {
      "conf_high": 0.501727,
      "conf_low": 0.413103,
      "estimate": 0.458555,
      "mode": "Web",
      "n": 1669,
      "n_eff": 1222,
      "outcome": "Government services",
      "row": "2016, web",
      "year": 2016
    },
    {
      "conf_high": 0.606637,
      "conf_low": 0.441333,
      "estimate": 0.528984,
      "mode": "Face-to-face",
      "n": 545,
      "n_eff": 294,
      "outcome": "Government services",
      "row": "2024, face-to-face",
      "year": 2024
    },
    {
      "conf_high": 0.52635,
      "conf_low": 0.405976,
      "estimate": 0.468333,
      "mode": "Web",
      "n": 1077,
      "n_eff": 648,
      "outcome": "Government services",
      "row": "2024, web",
      "year": 2024
    }
  ],
  "id": "spillover_mode",
  "notes": [
    "ANES 2020 has no mode weights, so it has no row. The 2024 panel and paper respondents are in neither mode. The defense item is left out because it was not asked in 2012."
  ],
  "source": "ANES Cumulative Data File, 2008-2024; weighted with the mode weights (weight_ftf for in-person rows, weight_web for web rows); white non-Hispanic respondents",
  "spec": {
    "colors": {
      "Face-to-face": "cat3",
      "Web": "cat4"
    },
    "facet": "outcome",
    "group": "mode",
    "hi": "conf_high",
    "lo": "conf_low",
    "n": "n",
    "sort": "data",
    "x": "estimate",
    "xDomain": [
      0,
      0.7
    ],
    "xFormat": {
      "digits": 2
    },
    "xLabel": "Correlation with the resentment index",
    "y": "row"
  },
  "subtitle": "Weighted correlation of the racial resentment index with each policy item, oriented so that a high value is the conservative position, by interview mode, white non-Hispanic respondents, years with mode weights",
  "table": {
    "columns": [
      {
        "key": "outcome",
        "label": "Item"
      },
      {
        "key": "row",
        "label": "Year and mode"
      },
      {
        "format": {
          "digits": 2,
          "signed": true
        },
        "key": "estimate",
        "label": "Correlation"
      },
      {
        "format": {
          "digits": 2,
          "signed": true
        },
        "key": "conf_low",
        "label": "Interval low"
      },
      {
        "format": {
          "digits": 2,
          "signed": true
        },
        "key": "conf_high",
        "label": "Interval high"
      },
      {
        "format": {
          "digits": 0,
          "thousands": true
        },
        "key": "n",
        "label": "Respondents"
      },
      {
        "format": {
          "digits": 0,
          "thousands": true
        },
        "key": "n_eff",
        "label": "Effective n"
      }
    ]
  },
  "title": "In 2012 web respondents' correlations with the health-insurance and government-services items were {fact:hl_web_2012} and {fact:sv_web_2012}, against {fact:hl_ftf_2012} and {fact:sv_ftf_2012} face-to-face",
  "type": "dot",
  "width": "wide"
}