{
  "schemaVersion": "ch4.aggregate.v1",
  "runId": "synthetic-validation",
  "planHash": "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
  "recipeId": "longitudinal",
  "recipeVersion": "2.0.0",
  "generatedAt": "2026-09-24T00:00:00.000Z",
  "dataQcProvenance": {
    "ch3CompletedAt": "2026-09-24T00:00:00.000Z",
    "dataUploadVersion": "synthetic-1",
    "qcReportVersion": "synthetic-1",
    "dataProfileHash": "synthetic",
    "qcReportHash": "synthetic",
    "payloadKind": "uploaded_qc",
    "rowCount": 1080,
    "columnCount": 5
  },
  "packageVersions": {
    "runtime": {
      "language": "r",
      "version": "4.6.1"
    },
    "packages": [
      {
        "name": "stats",
        "version": "4.6.1"
      },
      {
        "name": "jsonlite",
        "version": "2.0.0"
      },
      {
        "name": "lme4",
        "version": "2.0.6"
      },
      {
        "name": "lmerTest",
        "version": "3.2.1"
      }
    ]
  },
  "metrics": [
    {
      "metricId": "coefficient_1",
      "metricType": "effect_estimate",
      "labelZh": "纵向模型参数：(Intercept)",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 2.105822684275339,
        "scale": "mean_difference",
        "ci95Low": 1.798050993045835,
        "ci95High": 2.413594375504843,
        "pValue": 5.131388921129833e-29
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。"
    },
    {
      "metricId": "coefficient_2",
      "metricType": "effect_estimate",
      "labelZh": "纵向模型参数：group1",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 0.3716717632852938,
        "scale": "mean_difference",
        "ci95Low": -0.05451703321278034,
        "ci95High": 0.7978605597833679,
        "pValue": 0.08699496742874735
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。"
    },
    {
      "metricId": "coefficient_3",
      "metricType": "effect_estimate",
      "labelZh": "纵向模型参数：.__time",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 0.2920281638289459,
        "scale": "mean_difference",
        "ci95Low": 0.1941288125041817,
        "ci95High": 0.3899275151537102,
        "pValue": 1.920918028854582e-8
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。"
    },
    {
      "metricId": "coefficient_4",
      "metricType": "effect_estimate",
      "labelZh": "纵向模型参数：z",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 0.3128506491011341,
        "scale": "mean_difference",
        "ci95Low": 0.1202823746117645,
        "ci95High": 0.5054189235905038,
        "pValue": 0.001596518089614768
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。"
    },
    {
      "metricId": "coefficient_5",
      "metricType": "effect_estimate",
      "labelZh": "纵向模型参数：group1:.__time",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 0.2363238137495565,
        "scale": "mean_difference",
        "ci95Low": 0.1008510034864665,
        "ci95High": 0.3717966240126465,
        "pValue": 0.000718570477300678
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。"
    },
    {
      "metricId": "trajectory_1_1",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 0",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 2.102495807848677,
        "scale": "coefficient",
        "ci95Low": 1.794828097612864,
        "ci95High": 2.41016351808449
      },
      "plot": {
        "x": 0,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_2",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 0.25",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 2.175502848805913,
        "scale": "coefficient",
        "ci95Low": 1.8727147280581,
        "ci95High": 2.478290969553727
      },
      "plot": {
        "x": 0.25,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_3",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 0.5",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 2.24850988976315,
        "scale": "coefficient",
        "ci95Low": 1.948676429151284,
        "ci95High": 2.548343350375017
      },
      "plot": {
        "x": 0.5,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_4",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 0.75",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 2.321516930720386,
        "scale": "coefficient",
        "ci95Low": 2.022656061403617,
        "ci95High": 2.620377800037156
      },
      "plot": {
        "x": 0.75,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_5",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 1",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 2.394523971677623,
        "scale": "coefficient",
        "ci95Low": 2.094634325033522,
        "ci95High": 2.694413618321723
      },
      "plot": {
        "x": 1,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_6",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 1.25",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 2.46753101263486,
        "scale": "coefficient",
        "ci95Low": 2.164631627221188,
        "ci95High": 2.770430398048531
      },
      "plot": {
        "x": 1.25,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_7",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 1.5",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 2.540538053592096,
        "scale": "coefficient",
        "ci95Low": 2.23270610889048,
        "ci95High": 2.848369998293712
      },
      "plot": {
        "x": 1.5,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_8",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 1.75",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 2.613545094549333,
        "scale": "coefficient",
        "ci95Low": 2.298948259938253,
        "ci95High": 2.928141929160412
      },
      "plot": {
        "x": 1.75,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_9",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 2",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 2.686552135506569,
        "scale": "coefficient",
        "ci95Low": 2.363473226961195,
        "ci95High": 3.009631044051943
      },
      "plot": {
        "x": 2,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_10",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 2.25",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 2.759559176463805,
        "scale": "coefficient",
        "ci95Low": 2.426412209602579,
        "ci95High": 3.092706143325031
      },
      "plot": {
        "x": 2.25,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_11",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 2.5",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 2.832566217421042,
        "scale": "coefficient",
        "ci95Low": 2.487904222443282,
        "ci95High": 3.177228212398802
      },
      "plot": {
        "x": 2.5,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_12",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 2.75",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 2.905573258378278,
        "scale": "coefficient",
        "ci95Low": 2.548089109021469,
        "ci95High": 3.263057407735088
      },
      "plot": {
        "x": 2.75,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_13",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 3",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 2.978580299335515,
        "scale": "coefficient",
        "ci95Low": 2.607102229836519,
        "ci95High": 3.350058368834511
      },
      "plot": {
        "x": 3,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_14",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 3.25",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 3.051587340292751,
        "scale": "coefficient",
        "ci95Low": 2.665070857940365,
        "ci95High": 3.438103822645138
      },
      "plot": {
        "x": 3.25,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_15",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 3.5",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 3.124594381249988,
        "scale": "coefficient",
        "ci95Low": 2.722112069284951,
        "ci95High": 3.527076693215024
      },
      "plot": {
        "x": 3.5,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_16",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 3.75",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 3.197601422207224,
        "scale": "coefficient",
        "ci95Low": 2.778331805632903,
        "ci95High": 3.616871038781545
      },
      "plot": {
        "x": 3.75,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_17",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 4",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 3.270608463164461,
        "scale": "coefficient",
        "ci95Low": 2.833824776500774,
        "ci95High": 3.707392149828148
      },
      "plot": {
        "x": 4,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_18",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 4.25",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 3.343615504121698,
        "scale": "coefficient",
        "ci95Low": 2.888674909470495,
        "ci95High": 3.7985560987729
      },
      "plot": {
        "x": 4.25,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_19",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 4.5",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 3.416622545078934,
        "scale": "coefficient",
        "ci95Low": 2.942956121531617,
        "ci95High": 3.890288968626251
      },
      "plot": {
        "x": 4.5,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_20",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 4.75",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 3.48962958603617,
        "scale": "coefficient",
        "ci95Low": 2.996733247458578,
        "ci95High": 3.982525924613762
      },
      "plot": {
        "x": 4.75,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_1_21",
      "metricType": "effect_estimate",
      "labelZh": "组别 0；时间 5",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 3.562636626993406,
        "scale": "coefficient",
        "ci95Low": 3.050063014920156,
        "ci95High": 4.075210239066657
      },
      "plot": {
        "x": 5,
        "series": "组别 0"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_1",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 0",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 2.474167571133971,
        "scale": "coefficient",
        "ci95Low": 2.17991144257659,
        "ci95High": 2.768423699691352
      },
      "plot": {
        "x": 0,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_2",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 0.25",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 2.606255565528596,
        "scale": "coefficient",
        "ci95Low": 2.316667247504949,
        "ci95High": 2.895843883552244
      },
      "plot": {
        "x": 0.25,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_3",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 0.5",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 2.738343559923222,
        "scale": "coefficient",
        "ci95Low": 2.451581675057958,
        "ci95High": 3.025105444788486
      },
      "plot": {
        "x": 0.5,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_4",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 0.75",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 2.870431554317848,
        "scale": "coefficient",
        "ci95Low": 2.584600053379075,
        "ci95High": 3.15626305525662
      },
      "plot": {
        "x": 0.75,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_5",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 1",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 3.002519548712473,
        "scale": "coefficient",
        "ci95Low": 2.71570391602362,
        "ci95High": 3.289335181401326
      },
      "plot": {
        "x": 1,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_6",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 1.25",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 3.134607543107099,
        "scale": "coefficient",
        "ci95Low": 2.844912789022008,
        "ci95High": 3.424302297192189
      },
      "plot": {
        "x": 1.25,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_7",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 1.5",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 3.266695537501724,
        "scale": "coefficient",
        "ci95Low": 2.97228230240343,
        "ci95High": 3.561108772600019
      },
      "plot": {
        "x": 1.5,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_8",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 1.75",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 3.39878353189635,
        "scale": "coefficient",
        "ci95Low": 3.097899036783398,
        "ci95High": 3.699668027009302
      },
      "plot": {
        "x": 1.75,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_9",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 2",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 3.530871526290976,
        "scale": "coefficient",
        "ci95Low": 3.221873161878426,
        "ci95High": 3.839869890703525
      },
      "plot": {
        "x": 2,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_10",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 2.25",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 3.662959520685601,
        "scale": "coefficient",
        "ci95Low": 3.344330203298541,
        "ci95High": 3.981588838072661
      },
      "plot": {
        "x": 2.25,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_11",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 2.5",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 3.795047515080227,
        "scale": "coefficient",
        "ci95Low": 3.465403159722647,
        "ci95High": 4.124691870437807
      },
      "plot": {
        "x": 2.5,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_12",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 2.75",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 3.927135509474852,
        "scale": "coefficient",
        "ci95Low": 3.585225818807687,
        "ci95High": 4.269045200142018
      },
      "plot": {
        "x": 2.75,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_13",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 3",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 4.059223503869478,
        "scale": "coefficient",
        "ci95Low": 3.703927675315474,
        "ci95High": 4.414519332423483
      },
      "plot": {
        "x": 3,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_14",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 3.25",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 4.191311498264104,
        "scale": "coefficient",
        "ci95Low": 3.82163048336843,
        "ci95High": 4.560992513159777
      },
      "plot": {
        "x": 3.25,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_15",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 3.5",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 4.323399492658729,
        "scale": "coefficient",
        "ci95Low": 3.938446238968277,
        "ci95High": 4.708352746349181
      },
      "plot": {
        "x": 3.5,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_16",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 3.75",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 4.455487487053355,
        "scale": "coefficient",
        "ci95Low": 4.054476284340034,
        "ci95High": 4.856498689766675
      },
      "plot": {
        "x": 3.75,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_17",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 4",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 4.58757548144798,
        "scale": "coefficient",
        "ci95Low": 4.169811214891125,
        "ci95High": 5.005339748004835
      },
      "plot": {
        "x": 4,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_18",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 4.25",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 4.719663475842607,
        "scale": "coefficient",
        "ci95Low": 4.284531310650195,
        "ci95High": 5.154795641035019
      },
      "plot": {
        "x": 4.25,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_19",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 4.5",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 4.851751470237232,
        "scale": "coefficient",
        "ci95Low": 4.398707274679945,
        "ci95High": 5.304795665794518
      },
      "plot": {
        "x": 4.5,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_20",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 4.75",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 4.983839464631857,
        "scale": "coefficient",
        "ci95Low": 4.51240112158269,
        "ci95High": 5.455277807681024
      },
      "plot": {
        "x": 4.75,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "trajectory_2_21",
      "metricType": "effect_estimate",
      "labelZh": "组别 1；时间 5",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 5.115927459026483,
        "scale": "coefficient",
        "ci95Low": 4.625667110596428,
        "ci95High": 5.606187807456537
      },
      "plot": {
        "x": 5,
        "series": "组别 1"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。时间单位：月；数值协变量使用样本均值，分类协变量使用第一参照水平。"
    },
    {
      "metricId": "primary_effect",
      "metricType": "effect_estimate",
      "labelZh": "时间 0：组别 1 对比 0",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 0.3716717632852938,
        "scale": "mean_difference",
        "ci95Low": -0.05451703321278034,
        "ci95High": 0.7978605597833679,
        "pValue": 0.08699496742874735
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。联合协方差下的组间对比；时间与协变量参照已预先定义。"
    },
    {
      "metricId": "time_contrast_2",
      "metricType": "effect_estimate",
      "labelZh": "时间 5：组别 1 对比 0",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 1.553290832033076,
        "scale": "mean_difference",
        "ci95Low": 0.843733771434205,
        "ci95High": 2.262847892631948,
        "pValue": 0.0000259335680477568
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。联合协方差下的组间对比；时间与协变量参照已预先定义。"
    },
    {
      "metricId": "group_time_interaction",
      "metricType": "diagnostic_statistic",
      "labelZh": "组别与时间的联合交互检验",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 11.850385449414407,
        "scale": "coefficient",
        "pValue": 0.000718570477300678
      },
      "methodFootnoteSeedZh": "固定分析配方；直接检验组别随时间的效应差异；未以某一组的显著性推断交互。"
    },
    {
      "metricId": "individual_count",
      "metricType": "sample_count",
      "labelZh": "独立个体数",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 180,
        "scale": "count"
      },
      "methodFootnoteSeedZh": "固定分析配方；线性混合模型的固定效应平均轨迹。分析观测 1080 条，来自 180 位独立个体；缺失数量按观测条数计。"
    },
    {
      "metricId": "observation_count",
      "metricType": "sample_count",
      "labelZh": "实际参与建模的观测数",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 1080,
        "scale": "count"
      },
      "methodFootnoteSeedZh": "固定分析配方；原始记录 1080；结局缺失 0；时间单位 月。"
    },
    {
      "metricId": "flow_received",
      "metricType": "sample_count",
      "labelZh": "收到的分析输入记录",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 1080,
        "scale": "count"
      },
      "methodFootnoteSeedZh": "描述统计；主模型推断单位为原始个体，描述取每人首条观测；时变变量的首条值只用于描述；未上传的筛选与排除记录无法由平台推算。"
    },
    {
      "metricId": "flow_analyzed",
      "metricType": "sample_count",
      "labelZh": "主模型实际分析单位",
      "analyzedN": 180,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 180,
        "scale": "count"
      },
      "methodFootnoteSeedZh": "描述统计；主模型推断单位为原始个体，描述取每人首条观测；时变变量的首条值只用于描述；主模型推断单位为原始个体，描述取每人首条观测；时变变量的首条值只用于描述"
    },
    {
      "metricId": "flow_missing",
      "metricType": "sample_count",
      "labelZh": "缺失记录数量",
      "analyzedN": 1080,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 0,
        "scale": "count"
      },
      "methodFootnoteSeedZh": "描述统计；主模型推断单位为原始个体，描述取每人首条观测；时变变量的首条值只用于描述；缺失与其他排除分别记录，重复测量缺失数量按记录计。"
    },
    {
      "metricId": "flow_excluded",
      "metricType": "sample_count",
      "labelZh": "按分析规则排除的单位",
      "analyzedN": 180,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 0,
        "scale": "count"
      },
      "methodFootnoteSeedZh": "描述统计；主模型推断单位为原始个体，描述取每人首条观测；时变变量的首条值只用于描述；按配方明确的无效值或入组规则排除；不包含未提供的筛选人群。"
    },
    {
      "metricId": "baseline_1",
      "metricType": "sample_count",
      "labelZh": "总体；变量 group",
      "analyzedN": 180,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 180,
        "scale": "count"
      },
      "methodFootnoteSeedZh": "描述统计；主模型推断单位为原始个体，描述取每人首条观测；时变变量的首条值只用于描述；0：86 (47.8%)；1：94 (52.2%)；组内总数 180；百分比以非缺失数量为分母。"
    },
    {
      "metricId": "baseline_2",
      "metricType": "sample_count",
      "labelZh": "总体；变量 z",
      "analyzedN": 180,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 180,
        "scale": "count"
      },
      "methodFootnoteSeedZh": "描述统计；主模型推断单位为原始个体，描述取每人首条观测；时变变量的首条值只用于描述；均值 -0.010634；标准差 1.0769；中位数 -0.059077；Q1–Q3 -0.88888–0.72693；组内总数 180；百分比以非缺失数量为分母。"
    },
    {
      "metricId": "baseline_3",
      "metricType": "sample_count",
      "labelZh": "总体；变量 y",
      "analyzedN": 180,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 180,
        "scale": "count"
      },
      "methodFootnoteSeedZh": "描述统计；主模型推断单位为原始个体，描述取每人首条观测；时变变量的首条值只用于描述；均值 2.2014；标准差 1.6321；中位数 2.1728；Q1–Q3 1.1288–3.2272；组内总数 180；百分比以非缺失数量为分母。"
    },
    {
      "metricId": "baseline_4",
      "metricType": "sample_count",
      "labelZh": "暴露组 0；变量 group",
      "analyzedN": 86,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 86,
        "scale": "count"
      },
      "methodFootnoteSeedZh": "描述统计；主模型推断单位为原始个体，描述取每人首条观测；时变变量的首条值只用于描述；0：86 (100%)；1：0 (0%)；组内总数 86；百分比以非缺失数量为分母。"
    },
    {
      "metricId": "baseline_5",
      "metricType": "sample_count",
      "labelZh": "暴露组 0；变量 z",
      "analyzedN": 86,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 86,
        "scale": "count"
      },
      "methodFootnoteSeedZh": "描述统计；主模型推断单位为原始个体，描述取每人首条观测；时变变量的首条值只用于描述；均值 -0.086585；标准差 1.11；中位数 -0.11038；Q1–Q3 -0.95486–0.65361；组内总数 86；百分比以非缺失数量为分母。"
    },
    {
      "metricId": "baseline_6",
      "metricType": "sample_count",
      "labelZh": "暴露组 0；变量 y",
      "analyzedN": 86,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 86,
        "scale": "count"
      },
      "methodFootnoteSeedZh": "描述统计；主模型推断单位为原始个体，描述取每人首条观测；时变变量的首条值只用于描述；均值 1.9882；标准差 1.7067；中位数 1.7978；Q1–Q3 0.7537–2.813；组内总数 86；百分比以非缺失数量为分母。"
    },
    {
      "metricId": "baseline_7",
      "metricType": "sample_count",
      "labelZh": "暴露组 1；变量 group",
      "analyzedN": 94,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 94,
        "scale": "count"
      },
      "methodFootnoteSeedZh": "描述统计；主模型推断单位为原始个体，描述取每人首条观测；时变变量的首条值只用于描述；0：0 (0%)；1：94 (100%)；组内总数 94；百分比以非缺失数量为分母。"
    },
    {
      "metricId": "baseline_8",
      "metricType": "sample_count",
      "labelZh": "暴露组 1；变量 z",
      "analyzedN": 94,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 94,
        "scale": "count"
      },
      "methodFootnoteSeedZh": "描述统计；主模型推断单位为原始个体，描述取每人首条观测；时变变量的首条值只用于描述；均值 0.058853；标准差 1.0468；中位数 -0.025292；Q1–Q3 -0.79843–0.80466；组内总数 94；百分比以非缺失数量为分母。"
    },
    {
      "metricId": "baseline_9",
      "metricType": "sample_count",
      "labelZh": "暴露组 1；变量 y",
      "analyzedN": 94,
      "missingN": 0,
      "excludedN": 0,
      "estimate": {
        "value": 94,
        "scale": "count"
      },
      "methodFootnoteSeedZh": "描述统计；主模型推断单位为原始个体，描述取每人首条观测；时变变量的首条值只用于描述；均值 2.3965；标准差 1.5442；中位数 2.3858；Q1–Q3 1.4958–3.4157；组内总数 94；百分比以非缺失数量为分母。"
    }
  ],
  "diagnostics": [
    {
      "diagnosticId": "missingness_assumption",
      "severity": "info",
      "category": "missingness",
      "messageZh": "混合模型利用可用结局观测，依赖给定已建模信息的 MAR 假设；软件不能证明缺失机制。"
    }
  ],
  "tableSeeds": [
    {
      "tableSeedId": "model_coefficients",
      "purpose": "secondary_result_table",
      "metricIds": [
        "coefficient_1",
        "coefficient_2",
        "coefficient_3",
        "coefficient_4",
        "coefficient_5"
      ],
      "diagnosticIds": []
    },
    {
      "tableSeedId": "primary_result_table",
      "purpose": "primary_result_table",
      "metricIds": [
        "primary_effect",
        "time_contrast_2"
      ],
      "diagnosticIds": []
    },
    {
      "tableSeedId": "interaction_test",
      "purpose": "diagnostic_summary",
      "metricIds": [
        "group_time_interaction"
      ],
      "diagnosticIds": []
    },
    {
      "tableSeedId": "longitudinal_diagnostics",
      "purpose": "diagnostic_summary",
      "metricIds": [
        "individual_count",
        "observation_count"
      ],
      "diagnosticIds": []
    },
    {
      "tableSeedId": "participant_flow",
      "purpose": "diagnostic_summary",
      "metricIds": [
        "flow_received",
        "flow_analyzed",
        "flow_missing",
        "flow_excluded"
      ],
      "diagnosticIds": []
    },
    {
      "tableSeedId": "baseline_table_1",
      "purpose": "secondary_result_table",
      "metricIds": [
        "baseline_1",
        "baseline_2",
        "baseline_3",
        "baseline_4",
        "baseline_5",
        "baseline_6",
        "baseline_7",
        "baseline_8",
        "baseline_9"
      ],
      "diagnosticIds": []
    }
  ],
  "figureSeeds": [
    {
      "geometry": "curve",
      "xLabelZh": "时间（月）",
      "yLabelZh": "模型轨迹及区间",
      "figureSeedId": "effect_overview",
      "purpose": "effect_overview",
      "metricIds": [
        "trajectory_1_1",
        "trajectory_1_2",
        "trajectory_1_3",
        "trajectory_1_4",
        "trajectory_1_5",
        "trajectory_1_6",
        "trajectory_1_7",
        "trajectory_1_8",
        "trajectory_1_9",
        "trajectory_1_10",
        "trajectory_1_11",
        "trajectory_1_12",
        "trajectory_1_13",
        "trajectory_1_14",
        "trajectory_1_15",
        "trajectory_1_16",
        "trajectory_1_17",
        "trajectory_1_18",
        "trajectory_1_19",
        "trajectory_1_20",
        "trajectory_1_21",
        "trajectory_2_1",
        "trajectory_2_2",
        "trajectory_2_3",
        "trajectory_2_4",
        "trajectory_2_5",
        "trajectory_2_6",
        "trajectory_2_7",
        "trajectory_2_8",
        "trajectory_2_9",
        "trajectory_2_10",
        "trajectory_2_11",
        "trajectory_2_12",
        "trajectory_2_13",
        "trajectory_2_14",
        "trajectory_2_15",
        "trajectory_2_16",
        "trajectory_2_17",
        "trajectory_2_18",
        "trajectory_2_19",
        "trajectory_2_20",
        "trajectory_2_21"
      ],
      "diagnosticIds": []
    }
  ]
}