# Generated by `jof250 profiles build` — do not edit by hand (see docs/DATA_DICTIONARY.md)
profile: household_behavioral_finance
ontology_version: '1.0'
built:
  timestamp: '2026-11-03T23:29:47+00:00'
  code_version: f8b9e5a-dirty
  host:
    platform: macOS-27.0-arm64-arm-64bit
    python: 3.12.13
    machine: arm64
    node: MacBookPro-de-simon-pierre-2.local
selection_rule: subfield in {household_finance, behavioral_finance} (empirical/mixed)
n_documents: 32
split: train (heldout_v1 excluded)
caveat: Observed frequencies describe what published JoF articles did in 2017–2020; they are not evidence that these choices
  are editorially superior or required.
structure:
  pages:
    n: 32
    median: 42.5
    q25: 40.0
    q75: 45.25
    mean: 42.469
    min: 25.0
    max: 56.0
    median_ci95_bootstrap:
    - 40.5
    - 44.0
  n_words_body:
    n: 32
    median: 10576.5
    q25: 9716.5
    q75: 12793.5
    mean: 11042.125
    min: 6970.0
    max: 15440.0
    median_ci95_bootstrap:
    - 10074.663
    - 11856.7
  n_words_appendix:
    n: 32
    median: 0.0
    q25: 0.0
    q75: 21.25
    mean: 229.156
    min: 0.0
    max: 2531.0
    median_ci95_bootstrap:
    - 0.0
    - 10.5
  abstract_words:
    n: 32
    median: 99.5
    q25: 97.0
    q75: 103.5
    mean: 99.812
    min: 70.0
    max: 114.0
    median_ci95_bootstrap:
    - 98.0
    - 101.5
  n_sections:
    n: 32
    median: 5.0
    q25: 5.0
    q75: 6.25
    mean: 5.656
    min: 3.0
    max: 9.0
    median_ci95_bootstrap:
    - 5.0
    - 6.0
  n_subsections:
    n: 32
    median: 12.5
    q25: 9.0
    q75: 17.0
    mean: 14.219
    min: 5.0
    max: 46.0
    median_ci95_bootstrap:
    - 11.0
    - 15.0
  n_paragraphs:
    n: 32
    median: 92.0
    q25: 67.25
    q75: 114.0
    mean: 105.156
    min: 51.0
    max: 326.0
    median_ci95_bootstrap:
    - 71.0
    - 97.0
  n_equations:
    n: 32
    median: 2.0
    q25: 0.0
    q75: 7.25
    mean: 5.25
    min: 0.0
    max: 27.0
    median_ci95_bootstrap:
    - 1.0
    - 6.525
  n_tables:
    n: 32
    median: 8.0
    q25: 6.0
    q75: 11.0
    mean: 9.219
    min: 4.0
    max: 24.0
    median_ci95_bootstrap:
    - 7.0
    - 10.0
  n_figures:
    n: 32
    median: 4.0
    q25: 2.0
    q75: 7.0
    mean: 4.5
    min: 0.0
    max: 10.0
    median_ci95_bootstrap:
    - 2.738
    - 7.0
  n_footnotes:
    n: 32
    median: 33.0
    q25: 28.5
    q75: 42.0
    mean: 33.844
    min: 10.0
    max: 56.0
    median_ci95_bootstrap:
    - 29.5
    - 38.0
  n_references:
    n: 32
    median: 55.5
    q25: 44.75
    q75: 68.25
    mean: 59.688
    min: 17.0
    max: 122.0
    median_ci95_bootstrap:
    - 49.737
    - 64.0
  n_citations_in_text:
    n: 32
    median: 52.5
    q25: 38.75
    q75: 66.75
    mean: 61.812
    min: 17.0
    max: 181.0
    median_ci95_bootstrap:
    - 46.737
    - 63.0
  intro_words:
    n: 32
    median: 1829.5
    q25: 1598.5
    q75: 2063.0
    mean: 1858.656
    min: 1117.0
    max: 2536.0
    median_ci95_bootstrap:
    - 1707.5
    - 2020.412
  intro_paragraphs:
    n: 32
    median: 7.0
    q25: 7.0
    q75: 10.0
    mean: 8.469
    min: 4.0
    max: 18.0
    median_ci95_bootstrap:
    - 7.0
    - 8.0
  intro_share:
    n: 32
    median: 0.172
    q25: 0.156
    q75: 0.19
    mean: 0.172
    min: 0.101
    max: 0.265
    median_ci95_bootstrap:
    - 0.161
    - 0.184
  conclusion_words:
    n: 32
    median: 410.5
    q25: 319.0
    q75: 582.25
    mean: 580.375
    min: 172.0
    max: 3986.0
    median_ci95_bootstrap:
    - 349.0
    - 516.0
  conclusion_share:
    n: 32
    median: 0.038
    q25: 0.031
    q75: 0.051
    mean: 0.056
    min: 0.014
    max: 0.406
    median_ci95_bootstrap:
    - 0.033
    - 0.046
  theory_share:
    n: 32
    median: 0.0
    q25: 0.0
    q75: 0.146
    mean: 0.071
    min: 0.0
    max: 0.413
    median_ci95_bootstrap:
    - 0.0
    - 0.073
  data_share:
    n: 32
    median: 0.052
    q25: 0.0
    q75: 0.125
    mean: 0.097
    min: 0.0
    max: 0.57
    median_ci95_bootstrap:
    - 0.016
    - 0.112
  results_share:
    n: 32
    median: 0.0
    q25: 0.0
    q75: 0.196
    mean: 0.1
    min: 0.0
    max: 0.627
    median_ci95_bootstrap:
    - 0.0
    - 0.091
  robustness_share:
    n: 32
    median: 0.0
    q25: 0.0
    q75: 0.0
    mean: 0.031
    min: 0.0
    max: 0.239
    median_ci95_bootstrap:
    - 0.0
    - 0.0
  words_per_table:
    n: 32
    median: 1345.5
    q25: 991.557
    q75: 1807.812
    mean: 1401.35
    min: 371.917
    max: 2685.8
    median_ci95_bootstrap:
    - 1061.708
    - 1688.5
  refs_per_1000_words:
    n: 32
    median: 5.161
    q25: 3.96
    q75: 6.041
    mean: 5.526
    min: 2.331
    max: 10.145
    median_ci95_bootstrap:
    - 4.728
    - 5.962
  equations_per_1000_words:
    n: 32
    median: 0.218
    q25: 0.0
    q75: 0.723
    mean: 0.43
    min: 0.0
    max: 1.81
    median_ci95_bootstrap:
    - 0.111
    - 0.604
presence:
  has_robustness_section:
    n: 32
    share: 0.219
  has_literature_section:
    n: 32
    share: 0.25
  has_appendix:
    n: 32
    share: 0.344
  has_internet_appendix:
    n: 32
    share: 0.969
by_year:
  2017:
    n: 10
    n_words_body_median: 9972.5
    n_tables_median: 7.5
  2018:
    n: 8
    n_words_body_median: 9510.5
    n_tables_median: 10.5
  2019:
    n: 8
    n_words_body_median: 10987.5
    n_tables_median: 8.0
  2020:
    n: 6
    n_words_body_median: 12413.0
    n_tables_median: 9.5
rhetoric:
  n_annotated: 32
  genre:
    n: 32
    empirical: 0.781
    mixed_theory_empirical: 0.219
  subfield:
    n: 32
    household_finance: 0.688
    behavioral_finance: 0.312
  primary_method:
    n: 32
    reduced_form_regression: 0.406
    structural_estimation: 0.125
    survey_or_experiment: 0.125
    difference_in_differences: 0.125
    natural_experiment_event_study: 0.062
    instrumental_variables: 0.062
    calibration_simulation: 0.062
    regression_discontinuity: 0.031
  abstract_moves_present:
    question:
      n: 32
      share: 0.844
    gap:
      n: 32
      share: 0.062
    method:
      n: 32
      share: 0.906
    results:
      n: 32
      share: 1.0
    magnitude:
      n: 32
      share: 0.375
    contribution:
      n: 32
      share: 0.469
  abstract_move_order_median_sentence:
    question:
      n: 27
      median: 0.0
      q25: 0.0
      q75: 0.0
      mean: 0.074
      min: 0.0
      max: 1.0
      median_ci95_bootstrap:
      - 0.0
      - 0.0
    gap:
      n: 2
      median: 1.0
      q25: 1.0
      q75: 1.0
      mean: 1.0
      min: 1.0
      max: 1.0
      median_ci95_bootstrap:
      - 1.0
      - 1.0
    method:
      n: 29
      median: 1.0
      q25: 0.0
      q75: 1.0
      mean: 1.034
      min: 0.0
      max: 3.0
      median_ci95_bootstrap:
      - 1.0
      - 1.0
    results:
      n: 32
      median: 1.0
      q25: 1.0
      q75: 2.0
      mean: 1.438
      min: 0.0
      max: 4.0
      median_ci95_bootstrap:
      - 1.0
      - 2.0
    magnitude:
      n: 12
      median: 3.0
      q25: 2.0
      q75: 3.0
      mean: 2.417
      min: 0.0
      max: 4.0
      median_ci95_bootstrap:
      - 2.0
      - 3.0
    contribution:
      n: 15
      median: 3.0
      q25: 2.0
      q75: 4.0
      mean: 2.8
      min: 0.0
      max: 5.0
      median_ci95_bootstrap:
      - 1.0
      - 4.0
  abstract_sentences:
    n: 32
    median: 5.0
    q25: 4.0
    q75: 6.0
    mean: 5.188
    min: 3.0
    max: 9.0
    median_ci95_bootstrap:
    - 5.0
    - 6.0
  magnitude_in_abstract_regex:
    n: 32
    share: 0.312
  introduction:
    paragraphs:
      n: 32
      median: 7.0
      q25: 7.0
      q75: 10.0
      mean: 8.469
      min: 4.0
      max: 18.0
      median_ci95_bootstrap:
      - 7.0
      - 8.0
    words:
      n: 32
      median: 1126.0
      q25: 993.75
      q75: 1307.25
      mean: 1154.281
      min: 653.0
      max: 1855.0
      median_ci95_bootstrap:
      - 1035.0
      - 1274.0
    contribution_paragraph_index:
      n: 30
      median: 3.5
      q25: 0.25
      q75: 6.0
      mean: 4.133
      min: 0.0
      max: 14.0
      median_ci95_bootstrap:
      - 1.0
      - 5.0
    contribution_relative_position:
      n: 30
      median: 0.464
      q25: 0.017
      q75: 0.692
      mean: 0.414
      min: 0.0
      max: 0.929
      median_ci95_bootstrap:
      - 0.133
      - 0.625
    first_move:
      n: 32
      motivation: 0.938
      tension_or_puzzle: 0.031
      other: 0.031
    move_prevalence:
      n: 32
      preview_of_results:
        share: 1.0
        median_relative_position: 0.39
      motivation:
        share: 0.969
        median_relative_position: 0.0
      preview_of_approach:
        share: 0.938
        median_relative_position: 0.25
      contribution_statement:
        share: 0.812
        median_relative_position: 0.68
      related_literature_positioning:
        share: 0.781
        median_relative_position: 0.75
      mechanism_or_theory_sketch:
        share: 0.781
        median_relative_position: 0.56
      roadmap:
        share: 0.719
        median_relative_position: 1.0
      identification_defense:
        share: 0.656
        median_relative_position: 0.47
      tension_or_puzzle:
        share: 0.562
        median_relative_position: 0.11
      literature_gap:
        share: 0.5
        median_relative_position: 0.14
      policy_or_broader_implication:
        share: 0.438
        median_relative_position: 0.73
      robustness_mention:
        share: 0.344
        median_relative_position: 0.6
      other:
        share: 0.125
        median_relative_position: 0.36
    moves_per_intro:
      n: 32
      median: 12.0
      q25: 10.0
      q75: 14.0
      mean: 12.188
      min: 8.0
      max: 20.0
      median_ci95_bootstrap:
      - 10.0
      - 13.0
    common_move_sequences:
      n: 32
      ? tension_or_puzzle > literature_gap > contribution_statement > preview_of_approach > mechanism_or_theory_sketch > identification_defense
        > preview_of_approach > identification_defense > preview_of_results > preview_of_approach > preview_of_results > policy_or_broader_implication
        > related_literature_positioning > roadmap
      : 0.031
      ? motivation > literature_gap > preview_of_results > robustness_mention > identification_defense > contribution_statement
        > mechanism_or_theory_sketch > related_literature_positioning > roadmap
      : 0.031
      ? motivation > related_literature_positioning > contribution_statement > mechanism_or_theory_sketch > motivation > preview_of_approach
        > identification_defense > preview_of_results > identification_defense > robustness_mention > policy_or_broader_implication
      : 0.031
      ? motivation > literature_gap > mechanism_or_theory_sketch > tension_or_puzzle > preview_of_approach > preview_of_results
        > policy_or_broader_implication > contribution_statement > related_literature_positioning > roadmap
      : 0.031
      ? motivation > tension_or_puzzle > contribution_statement > mechanism_or_theory_sketch > preview_of_results > identification_defense
        > preview_of_approach > preview_of_results > preview_of_approach > identification_defense > preview_of_results > policy_or_broader_implication
        > roadmap
      : 0.031
      ? motivation > literature_gap > tension_or_puzzle > preview_of_approach > preview_of_results > other > identification_defense
        > preview_of_results > contribution_statement > roadmap
      : 0.031
    roadmap_present_llm:
      n: 32
      share: 0.719
    roadmap_present_regex:
      n: 32
      share: 0.719
    literature_positioning_location:
      n: 32
      inside_introduction: 0.812
      both: 0.125
      none: 0.031
      separate_section: 0.031
    contribution_types:
      n: 66
      new_evidence: 0.485
      new_data_or_measure: 0.197
      new_identification: 0.121
      new_theory_or_model: 0.091
      resolution_of_puzzle: 0.076
      new_method: 0.03
  identification:
    causal_language_strength:
      n: 32
      median: 3.0
      q25: 3.0
      q75: 4.0
      mean: 3.219
      min: 2.0
      max: 5.0
      median_ci95_bootstrap:
      - 3.0
      - 4.0
    uses_causal_claim:
      n: 32
      share: 0.781
  results:
    economic_significance_discussed:
      n: 32
      share: 0.938
    statistical_language:
      n: 32
      unclear: 0.656
      stars_and_tstats: 0.219
      mixed: 0.094
      p_values: 0.031
    magnitude_statements_in_intro:
      n: 32
      share: 0.844
  robustness:
    location:
      n: 32
      mixed: 0.344
      within_results: 0.312
      none_seen: 0.125
      main_text_section: 0.125
      appendix: 0.062
      internet_appendix: 0.031
    types:
      n: 96
      alternative_specification: 0.26
      subsample: 0.229
      other: 0.188
      alternative_measure: 0.115
      falsification: 0.052
      placebo: 0.052
      sensitivity_to_parameters: 0.042
      ? ''
      : 0.042
  tables:
    standard_errors:
      n: 32
      unclear: 0.688
      clustered: 0.188
      robust: 0.062
      none: 0.031
      newey_west: 0.031
    units_in_notes:
      n: 32
      share: 0.812
    clustered_regex:
      n: 32
      share: 0.156
  figures:
    uncertainty_shown:
      n: 32
      unclear: 0.531
      'no': 0.156
      mixed: 0.156
      no_figures: 0.156
  conclusion:
    bounded_claims:
      n: 32
      share: 0.812
    policy_implications:
      n: 32
      share: 0.5
    open_questions:
      n: 32
      share: 0.5
  hedging:
    n: 32
    moderate: 0.938
    low: 0.062
  claims_with_stated_evidence_share:
    n: 32
    median: 1.0
    q25: 1.0
    q75: 1.0
    mean: 0.996
    min: 0.857
    max: 1.0
    median_ci95_bootstrap:
    - 1.0
    - 1.0
  llm_vs_rule_section_role_agreement:
    n: 32
    median: 0.911
    q25: 0.75
    q75: 1.0
    mean: 0.871
    min: 0.6
    max: 1.0
    median_ci95_bootstrap:
    - 0.783
    - 1.0
  llm_confidence:
    n: 32
    median: 0.8
    q25: 0.8
    q75: 0.827
    mean: 0.814
    min: 0.8
    max: 0.85
    median_ci95_bootstrap:
    - 0.8
    - 0.82