{
  "alt": "Dot chart with two panels and interval lines. The top panel shows changes in the party gap: {fact:mo_a_0812_ftf} points for in-person ANES respondents from 2008 to 2012, {fact:mo_a_1620_web} for ANES web respondents in 2016 against all respondents in 2020, {fact:mo_a_2024_web} from 2020 to web respondents in 2024, {fact:mo_g_0810_ftf} for in-person GSS respondents from 2008 to 2010, {fact:st_g_2018_2022} for all GSS respondents from 2018 to 2022, {fact:mo_g_1822_ftf} for in-person GSS respondents over the same years, {fact:mo_g_2124_web} for GSS web respondents from 2021 to 2024 and {fact:mo_s_2124_web} for the GSS spending item among web respondents. The bottom panel shows web minus in-person gaps: {fact:mo_a_diff_2012} points in the 2012 ANES, {fact:mo_a_diff_2016} in 2016, {fact:mo_a_diff_2024} in 2024, {fact:mo_g_diff_2022} in the 2022 GSS and {fact:mo_g_diff_2024} in 2024.",
  "caption": "In the top panel the ANES comparison of 2016 web respondents with all 2020 respondents is above zero with an interval that excludes zero. The GSS change from 2018 to 2022 is {fact:st_g_2018_2022} points among all respondents and {fact:mo_g_1822_ftf} points among in-person respondents, both with intervals that include zero. In the bottom panel only the GSS 2024 difference between web and in-person gaps excludes zero. Dots are estimates and lines are 95% confidence intervals. The 2020 ANES study has no mode weights, so two rows compare one mode with all respondents in 2020, and the 2016, 2020 and 2024 rows share panel respondents, which the intervals ignore.",
  "data": [
    {
      "comparison": "ANES in person, 2008 to 2012",
      "conf_high": 17.8418,
      "conf_low": -1.47023,
      "estimate": 8.18577,
      "n": 2570,
      "panel": "Change in the gap within or across modes"
    },
    {
      "comparison": "ANES web 2016 to all 2020",
      "conf_high": 20.6276,
      "conf_low": 10.5673,
      "estimate": 15.5974,
      "n": 8895,
      "panel": "Change in the gap within or across modes"
    },
    {
      "comparison": "ANES all 2020 to web 2024",
      "conf_high": 1.23648,
      "conf_low": -11.0648,
      "estimate": -4.91417,
      "n": 8244,
      "panel": "Change in the gap within or across modes"
    },
    {
      "comparison": "GSS in person, 2008 to 2010",
      "conf_high": 20.8573,
      "conf_low": 0.23943,
      "estimate": 10.5484,
      "n": 1909,
      "panel": "Change in the gap within or across modes"
    },
    {
      "comparison": "GSS all respondents, 2018 to 2022",
      "conf_high": 11.7138,
      "conf_low": -7.95008,
      "estimate": 1.88184,
      "n": 2906,
      "panel": "Change in the gap within or across modes"
    },
    {
      "comparison": "GSS in person, 2018 to 2022",
      "conf_high": 6.80311,
      "conf_low": -18.8982,
      "estimate": -6.04755,
      "n": 1848,
      "panel": "Change in the gap within or across modes"
    },
    {
      "comparison": "GSS web, 2021 to 2024",
      "conf_high": 13.9046,
      "conf_low": -5.82048,
      "estimate": 4.04205,
      "n": 2586,
      "panel": "Change in the gap within or across modes"
    },
    {
      "comparison": "GSS spending, web, 2021 to 2024",
      "conf_high": -7.72213,
      "conf_low": -29.7242,
      "estimate": -18.7232,
      "n": 1919,
      "panel": "Change in the gap within or across modes"
    },
    {
      "comparison": "ANES 2012",
      "conf_high": 9.4101,
      "conf_low": -4.41379,
      "estimate": 2.49815,
      "n": 4760,
      "panel": "Web minus in-person gap, same year"
    },
    {
      "comparison": "ANES 2016",
      "conf_high": 3.02664,
      "conf_low": -12.9248,
      "estimate": -4.94909,
      "n": 3294,
      "panel": "Web minus in-person gap, same year"
    },
    {
      "comparison": "ANES 2024",
      "conf_high": 11.4376,
      "conf_low": -7.97964,
      "estimate": 1.72896,
      "n": 2588,
      "panel": "Web minus in-person gap, same year"
    },
    {
      "comparison": "GSS 2022",
      "conf_high": 25.2046,
      "conf_low": -3.47979,
      "estimate": 10.8624,
      "n": 1541,
      "panel": "Web minus in-person gap, same year"
    },
    {
      "comparison": "GSS 2024",
      "conf_high": 30.7186,
      "conf_low": 2.83385,
      "estimate": 16.7762,
      "n": 1373,
      "panel": "Web minus in-person gap, same year"
    }
  ],
  "id": "mode_check",
  "notes": [
    "The 2024 ANES mode groups are the fresh in-person and fresh web samples; the panel respondents are in neither. The ANES 2008 study was in person only. GSS in-person rows leave out phone and other interviews, and the 2021 GSS has no in-person group, so the in-person comparison runs from 2018 to 2022.",
    "The GSS spending row is the only row about the spending question; every other GSS row is the help-pay question. Cells need at least 100 respondents and an effective sample of at least 100 in each party."
  ],
  "source": "ANES Cumulative Data File, 2008 to 2024, and General Social Survey, 2008 to 2024; weighted (weight_ftf and weight_web, the ANES weights for each mode; weight_use)",
  "spec": {
    "facet": "panel",
    "hi": "conf_high",
    "lo": "conf_low",
    "n": "n",
    "reference": 0,
    "sort": "data",
    "x": "estimate",
    "xDomain": [
      -35,
      35
    ],
    "xFormat": {
      "digits": 1
    },
    "xLabel": "Change or difference (percentage points)",
    "y": "comparison"
  },
  "subtitle": "Changes in the Democratic minus Republican gap within one interview mode, and web minus in-person differences in the same year; leaners included; 95% intervals",
  "table": {
    "columns": [
      {
        "key": "panel",
        "label": "Panel"
      },
      {
        "key": "comparison",
        "label": "Comparison"
      },
      {
        "format": {
          "digits": 1
        },
        "key": "estimate",
        "label": "Estimate (points)"
      },
      {
        "format": {
          "digits": 1
        },
        "key": "conf_low",
        "label": "Lower"
      },
      {
        "format": {
          "digits": 1
        },
        "key": "conf_high",
        "label": "Upper"
      },
      {
        "format": {
          "thousands": true
        },
        "key": "n",
        "label": "Respondents"
      }
    ]
  },
  "title": "The ANES gap was higher in 2020 than among 2016 web respondents, and the in-person GSS gap in 2022 cannot be told from its 2018 level",
  "type": "dot",
  "width": "body"
}