{
  "status": "Proposed teaching specifications; adapt and pilot before project collection",
  "synthetic_data_dictionary": [
    {"variable": "household_id", "type": "string", "unit": "household", "definition": "Persistent fictional household identifier; contains no real identity"},
    {"variable": "stratum", "type": "string", "unit": "household", "definition": "Mutually exclusive fictional sampling stratum"},
    {"variable": "N_h", "type": "integer", "unit": "households", "definition": "Number of eligible households in the stratum frame"},
    {"variable": "n_h", "type": "integer", "unit": "households", "definition": "Number selected without replacement in the stratum"},
    {"variable": "base_weight", "type": "number", "unit": "represented households per selected household", "definition": "N_h divided by n_h; baseline response is complete"},
    {"variable": "inclusion_probability", "type": "number", "unit": "probability", "definition": "n_h divided by N_h"},
    {"variable": "household_size", "type": "integer", "unit": "people", "definition": "Fictional eligible consumption roster count; held constant across rounds for this demonstration"},
    {"variable": "water_disruption_7d", "type": "binary", "unit": "household", "definition": "At least one disruption in the specified fictional seven-day period; 1 yes and 0 no; does not measure water quality"},
    {"variable": "resource_dependence", "type": "binary", "unit": "household", "definition": "Fictional screening status; not a validated vulnerability scale or official indicator"},
    {"variable": "consumption_baseline_nominal", "type": "number", "unit": "abstract local currency units per household per month", "definition": "Synthetic household consumption; not a national poverty aggregate"},
    {"variable": "consumption_followup_nominal", "type": "number or null", "unit": "abstract local currency units per household per month", "definition": "Synthetic follow-up consumption; null means no reinterview, not zero"},
    {"variable": "consumption_baseline_real_pc", "type": "number", "unit": "baseline-price abstract currency per person per month", "definition": "Baseline consumption divided by eligible household size; base index 100"},
    {"variable": "price_index_baseline", "type": "number", "unit": "index", "definition": "Assumed 100 for the teaching example"},
    {"variable": "price_index_followup", "type": "number", "unit": "index", "definition": "Assumed 110 for the teaching example; not a retrieved CPI"},
    {"variable": "response_baseline", "type": "string", "unit": "interview", "definition": "Complete for all selected synthetic baseline households"},
    {"variable": "response_followup", "type": "string", "unit": "interview", "definition": "Complete or not_reinterviewed; attrition is deliberately selective"}
  ],
  "proposed_project_question_specifications": [
    {
      "variable": "water_disruption_7d",
      "wording": "During the last seven days, was there any day when your household could not obtain water from its usual source?",
      "respondent": "Household member knowledgeable about water collection",
      "universe": "All eligible interviewed households",
      "codes": {"yes": 1, "no": 0},
      "missingness": "Use a separate response-status field and null numerical value",
      "analysis": "Weighted household share with observed answers; report eligible, observed, and missing counts",
      "limitations": "Proposed wording; does not establish safe drinking water or an SDG service level"
    },
    {
      "variable": "water_roundtrip_minutes",
      "wording": "On your most recent collection trip, how many minutes did the journey, waiting, and return take in total?",
      "respondent": "Person who undertook the trip, where feasible",
      "universe": "Households with a collection trip in the specified period",
      "unit": "Minutes per specified round trip",
      "analysis": "Distribution among eligible collecting households; preserve no-trip and piped-supply statuses",
      "limitations": "Record date, mode, collector, and source; one trip is not necessarily a seasonal average"
    },
    {
      "variable": "activity_net_cash_earnings",
      "wording": "Use separate activity-specific questions for receipts, operating costs, and reference period",
      "respondent": "Activity participant or manager",
      "universe": "Activities identified through screening and repeats",
      "unit": "Local currency per defined activity period",
      "analysis": "Receipts minus consistently defined operating costs; retain own consumption separately",
      "limitations": "Do not subtract household consumption or double-count joint inputs; not automatically accounting profit"
    },
    {
      "variable": "used_land_restricted_share",
      "wording": "Link verified land-use records to the versioned footprint and restriction period",
      "respondent": "User plus appropriate asset/inventory verification",
      "universe": "Households with positive used area under the defined land-use measure",
      "unit": "Area fraction",
      "analysis": "Restricted used area divided by total used area; remove overlaps and define shared-use treatment",
      "limitations": "Physical exposure; does not determine entitlement or percentage income loss"
    }
  ]
}