{
  "alt": "A figure with three tabs. The first is a line chart of mean ladder scores for partnered and other adults across ten deciles of county social capital, both nearly flat. The second is a line chart of the premium, {fact:comp_gap_lo} ladder points in the lowest decile and {fact:comp_gap_hi} in the highest. The third is a dot plot of seven small positive interaction coefficients.",
  "caption": "The first tab shows the two groups' ladder scores, the second the premium between them, and the third how the premium changes with each of seven county measures. Respondents are people, but the social capital measures describe their counties, so the comparison says how the premium differs across kinds of place and not what a county does for a person.",
  "data": [],
  "id": "partner_premium_by_social_capital",
  "notes": [
    "Gallup's extract has no survey weights, so every estimate is unweighted and levels can differ from the weighted figures Gallup publishes. County comes from the respondent's ZIP code and is approximate near county lines. The ladder is the evaluative measure, and daily feelings are not used here.",
    "Deciles hold about a tenth of interviews each, and a county sits in one decile. The JEC index combines family unity, community health, institutional health and collective efficacy, and family unity includes the share of women who are married, so the Atlas measures serve as a check that does not depend on marriage.",
    "The premium in the second tab is largest in one of the upper deciles; the highest of the ten estimates is selected for being the highest.",
    "The third tab clusters errors on the respondent's state, because the JEC community-health and institutional-health subindexes include state-level inputs; the first two tabs cluster on county."
  ],
  "source": "Gallup U.S. Daily, 2009-2017, unweighted, intervals clustered by county (by state in the third tab); JEC Social Capital Index 2018 release (components 2010-2016) and Social Capital Atlas 2022 joined on the county of the interview",
  "spec": {
    "panels": [
      {
        "figure": {
          "alt": "Line chart of the mean ladder score across ten deciles of county social capital for two groups. The partnered line sits above the other line at every decile and both lines are nearly flat.",
          "caption": "The two lines run roughly parallel and flat, with the partnered line higher at every decile. Each point is an unweighted mean with a 95% interval clustered by county.",
          "data": [
            {
              "conf_high": 7.297,
              "conf_low": 7.205,
              "decile": 1,
              "estimate": 7.251,
              "group": "Married or domestic partner",
              "n": 112277
            },
            {
              "conf_high": 6.844,
              "conf_low": 6.752,
              "decile": 1,
              "estimate": 6.798,
              "group": "Single, separated, divorced or widowed",
              "n": 106246
            },
            {
              "conf_high": 7.301,
              "conf_low": 7.229,
              "decile": 2,
              "estimate": 7.265,
              "group": "Married or domestic partner",
              "n": 119477
            },
            {
              "conf_high": 6.849,
              "conf_low": 6.772,
              "decile": 2,
              "estimate": 6.81,
              "group": "Single, separated, divorced or widowed",
              "n": 97396
            },
            {
              "conf_high": 7.304,
              "conf_low": 7.244,
              "decile": 3,
              "estimate": 7.274,
              "group": "Married or domestic partner",
              "n": 117601
            },
            {
              "conf_high": 6.846,
              "conf_low": 6.775,
              "decile": 3,
              "estimate": 6.811,
              "group": "Single, separated, divorced or widowed",
              "n": 101443
            },
            {
              "conf_high": 7.283,
              "conf_low": 7.223,
              "decile": 4,
              "estimate": 7.253,
              "group": "Married or domestic partner",
              "n": 125048
            },
            {
              "conf_high": 6.77,
              "conf_low": 6.71,
              "decile": 4,
              "estimate": 6.74,
              "group": "Single, separated, divorced or widowed",
              "n": 92165
            },
            {
              "conf_high": 7.291,
              "conf_low": 7.227,
              "decile": 5,
              "estimate": 7.259,
              "group": "Married or domestic partner",
              "n": 126801
            },
            {
              "conf_high": 6.782,
              "conf_low": 6.705,
              "decile": 5,
              "estimate": 6.743,
              "group": "Single, separated, divorced or widowed",
              "n": 91539
            },
            {
              "conf_high": 7.284,
              "conf_low": 7.219,
              "decile": 6,
              "estimate": 7.251,
              "group": "Married or domestic partner",
              "n": 131967
            },
            {
              "conf_high": 6.79,
              "conf_low": 6.704,
              "decile": 6,
              "estimate": 6.747,
              "group": "Single, separated, divorced or widowed",
              "n": 90649
            },
            {
              "conf_high": 7.29,
              "conf_low": 7.233,
              "decile": 7,
              "estimate": 7.261,
              "group": "Married or domestic partner",
              "n": 129786
            },
            {
              "conf_high": 6.767,
              "conf_low": 6.703,
              "decile": 7,
              "estimate": 6.735,
              "group": "Single, separated, divorced or widowed",
              "n": 83949
            },
            {
              "conf_high": 7.301,
              "conf_low": 7.252,
              "decile": 8,
              "estimate": 7.276,
              "group": "Married or domestic partner",
              "n": 134032
            },
            {
              "conf_high": 6.792,
              "conf_low": 6.732,
              "decile": 8,
              "estimate": 6.762,
              "group": "Single, separated, divorced or widowed",
              "n": 81701
            },
            {
              "conf_high": 7.35,
              "conf_low": 7.29,
              "decile": 9,
              "estimate": 7.32,
              "group": "Married or domestic partner",
              "n": 135115
            },
            {
              "conf_high": 6.825,
              "conf_low": 6.763,
              "decile": 9,
              "estimate": 6.794,
              "group": "Single, separated, divorced or widowed",
              "n": 82489
            },
            {
              "conf_high": 7.374,
              "conf_low": 7.326,
              "decile": 10,
              "estimate": 7.35,
              "group": "Married or domestic partner",
              "n": 141007
            },
            {
              "conf_high": 6.888,
              "conf_low": 6.829,
              "decile": 10,
              "estimate": 6.859,
              "group": "Single, separated, divorced or widowed",
              "n": 79202
            }
          ],
          "id": "ladder_by_social_capital",
          "spec": {
            "colors": {
              "Married or domestic partner": "accent",
              "Single, separated, divorced or widowed": "muted"
            },
            "hi": "conf_high",
            "lo": "conf_low",
            "n": "n",
            "series": "group",
            "x": "decile",
            "xDomain": [
              1,
              10
            ],
            "xLabel": "Decile of the county Social Capital Index (1 = lowest tenth of interviews, 10 = highest)",
            "xTicks": "data",
            "y": "estimate",
            "yDomain": [
              6.4,
              7.6
            ],
            "yFormat": {
              "digits": 1
            },
            "yLabel": "Mean ladder score (0 to 10)"
          },
          "subtitle": "Unweighted mean Cantril ladder score by decile of the JEC Social Capital Index of the respondent's county, Gallup U.S. Daily interviews 2009 to 2017",
          "title": "Ladder scores differ little between the lowest and highest decile of county social capital, {fact:comp_partnered_lo} and {fact:comp_partnered_hi} among partnered adults and {fact:comp_other_lo} and {fact:comp_other_hi} among others",
          "type": "line"
        },
        "label": "Ladder scores"
      },
      {
        "figure": {
          "alt": "Line chart of the partner premium across ten deciles of county social capital. The line starts at {fact:comp_gap_lo} ladder points in the lowest decile, is higher in the middle and upper deciles, and is {fact:comp_gap_hi} in the highest decile.",
          "caption": "The point estimates are smaller in the three lowest deciles than in the seven others, although some intervals overlap, and the premium does not shrink as county social capital rises. Each point is a difference of means with a 95% interval clustered by county.",
          "data": [
            {
              "conf_high": 0.479,
              "conf_low": 0.427,
              "decile": 1,
              "estimate": 0.453,
              "n": 218523
            },
            {
              "conf_high": 0.486,
              "conf_low": 0.423,
              "decile": 2,
              "estimate": 0.455,
              "n": 216873
            },
            {
              "conf_high": 0.495,
              "conf_low": 0.431,
              "decile": 3,
              "estimate": 0.463,
              "n": 219044
            },
            {
              "conf_high": 0.534,
              "conf_low": 0.492,
              "decile": 4,
              "estimate": 0.513,
              "n": 217213
            },
            {
              "conf_high": 0.536,
              "conf_low": 0.495,
              "decile": 5,
              "estimate": 0.515,
              "n": 218340
            },
            {
              "conf_high": 0.525,
              "conf_low": 0.483,
              "decile": 6,
              "estimate": 0.504,
              "n": 222616
            },
            {
              "conf_high": 0.546,
              "conf_low": 0.507,
              "decile": 7,
              "estimate": 0.527,
              "n": 213735
            },
            {
              "conf_high": 0.536,
              "conf_low": 0.492,
              "decile": 8,
              "estimate": 0.514,
              "n": 215733
            },
            {
              "conf_high": 0.548,
              "conf_low": 0.504,
              "decile": 9,
              "estimate": 0.526,
              "n": 217604
            },
            {
              "conf_high": 0.511,
              "conf_low": 0.472,
              "decile": 10,
              "estimate": 0.491,
              "n": 220209
            }
          ],
          "id": "premium_by_social_capital",
          "spec": {
            "annotations": [
              {
                "label": "All counties",
                "type": "y-rule",
                "y": 0.5
              }
            ],
            "hi": "conf_high",
            "lo": "conf_low",
            "n": "n",
            "x": "decile",
            "xDomain": [
              1,
              10
            ],
            "xLabel": "Decile of the county Social Capital Index (1 = lowest tenth of interviews, 10 = highest)",
            "xTicks": "data",
            "y": "estimate",
            "yDomain": [
              0,
              0.8
            ],
            "yFormat": {
              "digits": 1
            },
            "yLabel": "Partner premium (ladder points)"
          },
          "subtitle": "Unweighted difference in mean ladder score, partnered minus other adults, by decile of the JEC Social Capital Index of the respondent's county, 2009 to 2017",
          "title": "The partner premium is {fact:comp_gap_lo} ladder points in the lowest decile of county social capital and {fact:comp_gap_hi} in the highest",
          "type": "line"
        },
        "label": "Partner premium"
      },
      {
        "figure": {
          "alt": "Dot plot of seven coefficients, all right of zero and all small, from {fact:inter_min} to {fact:inter_max} ladder points per standard deviation. {fact:inter_n_zero} of the intervals include zero.",
          "caption": "Every point estimate is right of zero, so no measure goes with a smaller premium in these data, but {fact:inter_n_zero} of the intervals include zero (community health, institutional health and civic groups). Each dot is the coefficient on partnership times the county measure, with a 95% interval clustered by state.",
          "data": [
            {
              "conf_high": 0.034,
              "conf_low": 0.0121,
              "estimate": 0.0231,
              "measure": "JEC Social Capital Index",
              "n": 2179890,
              "source": "JEC Social Capital Project"
            },
            {
              "conf_high": 0.0392,
              "conf_low": 0.0176,
              "estimate": 0.0284,
              "measure": "JEC family unity",
              "n": 2182603,
              "source": "JEC Social Capital Project"
            },
            {
              "conf_high": 0.0331,
              "conf_low": -0.0097,
              "estimate": 0.0117,
              "measure": "JEC community health",
              "n": 2188939,
              "source": "JEC Social Capital Project"
            },
            {
              "conf_high": 0.0189,
              "conf_low": -0.0052,
              "estimate": 0.0068,
              "measure": "JEC institutional health",
              "n": 2186233,
              "source": "JEC Social Capital Project"
            },
            {
              "conf_high": 0.0213,
              "conf_low": 0.0069,
              "estimate": 0.0141,
              "measure": "JEC collective efficacy (low violent crime)",
              "n": 2174228,
              "source": "JEC Social Capital Project"
            },
            {
              "conf_high": 0.0387,
              "conf_low": -0.002,
              "estimate": 0.0184,
              "measure": "Civic groups per capita",
              "n": 2185410,
              "source": "Social Capital Atlas"
            },
            {
              "conf_high": 0.0506,
              "conf_low": 0.0188,
              "estimate": 0.0347,
              "measure": "Volunteering group membership",
              "n": 2185410,
              "source": "Social Capital Atlas"
            }
          ],
          "id": "premium_by_community_measure",
          "spec": {
            "colors": {
              "JEC Social Capital Project": "cat1",
              "Social Capital Atlas": "cat2"
            },
            "group": "source",
            "hi": "conf_high",
            "lo": "conf_low",
            "n": "n",
            "reference": 0,
            "referenceLabel": "No change",
            "sort": "desc",
            "x": "estimate",
            "xDomain": [
              -0.02,
              0.06
            ],
            "xFormat": {
              "digits": 3,
              "signed": true
            },
            "xLabel": "Change in the partner premium per standard deviation of the county measure (ladder points)",
            "y": "measure"
          },
          "subtitle": "Change in the partner premium (ladder points) per standard deviation of each county measure, interaction coefficients from regressions of the ladder score, 2009 to 2017",
          "title": "The partner premium is {fact:inter_min} to {fact:inter_max} ladder points larger for each standard deviation of the seven county community measures",
          "type": "dot"
        },
        "label": "Change per standard deviation"
      }
    ]
  },
  "subtitle": "Cantril ladder scores of partnered and other adults by decile of the JEC Social Capital Index of the respondent's county, and the change in the premium per standard deviation of seven county measures",
  "title": "The partner premium does not shrink where county social capital is higher: {fact:comp_gap_lo} ladder points in the lowest decile and {fact:comp_gap_hi} in the highest",
  "type": "tabs",
  "width": "wide"
}