feat: impute below-threshold student loan borrowers

changelog.yaml

@@ -576,3 +576,11 @@
     - Upload datasets to public HuggingFace repo (policyengine/policyengine-uk-data)
       in addition to private repo, so policyengine-uk gets the latest data.
   date: 2026-02-23 13:26:29
+- bump: minor
+  changes:
+    added:
+    - SLC "liable to repay" targets for Plan 2 and Plan 5, covering all borrowers
+      including those below repayment threshold.
+    - Probabilistic imputation of below-threshold student loan borrowers based on
+      tertiary education, age, and SLC forecast data.
+  date: 2026-02-23 16:00:00

changelog_entry.yaml

@@ -0,0 +1,7 @@
+- bump: minor
+  changes:
+    added:
+    - SLC "liable to repay" targets for Plan 2 and Plan 5, covering all borrowers
+      including those below repayment threshold.
+    - Probabilistic imputation of below-threshold student loan borrowers based on
+      tertiary education, age, and SLC forecast data.

policyengine_uk_data/datasets/frs.py

@@ -208,43 +208,101 @@ def determine_education_level(fted_val, typeed2_val, age_val):
     )
 
     # Add highest education from EDUCQUAL (highest qualification achieved)
-    # Codes from FRS ADT_324X classification; unmapped codes default to UPPER_SECONDARY
+    # Based on FRS 2022-23 documentation (SPSS value labels)
     EDUCQUAL_MAP = {
-        1: "NOT_COMPLETED_PRIMARY",
-        2: "LOWER_SECONDARY",  # GCSE D-G / CSE 2-5
-        3: "LOWER_SECONDARY",  # GCSE A-C / O-level A-C
-        4: "UPPER_SECONDARY",  # AS-level
-        5: "UPPER_SECONDARY",  # A-level (1 subject)
-        6: "UPPER_SECONDARY",  # A-level (2 subjects)
-        7: "UPPER_SECONDARY",  # A-level (3+ subjects)
-        8: "LOWER_SECONDARY",  # Scottish Standard/Ordinary Grade
-        9: "UPPER_SECONDARY",  # Scottish Higher Grade
-        10: "UPPER_SECONDARY",  # Scottish 6th Year Studies
+        # Degree level and above (TERTIARY)
+        1: "TERTIARY",  # Doctorate or MPhil
+        2: "TERTIARY",  # Masters, PGCE or other postgrad
+        3: "TERTIARY",  # Degree inc foundation degree
+        4: "TERTIARY",  # Teaching qualification (excl PGCE)
+        5: "TERTIARY",  # Foreign qualification at degree level
+        6: "TERTIARY",  # Other work-related qual at degree level
+        7: "TERTIARY",  # Other professional qual at degree level
+        # Higher education below degree (POST_SECONDARY)
+        8: "POST_SECONDARY",  # Other HE qualification below degree
+        9: "POST_SECONDARY",  # Nursing or other medical
+        10: "POST_SECONDARY",  # Diploma in higher education
         11: "POST_SECONDARY",  # HNC/HND
-        12: "POST_SECONDARY",  # City & Guilds advanced / BTEC National
-        13: "UPPER_SECONDARY",  # City & Guilds craft / BTEC General
-        14: "POST_SECONDARY",  # ONC/OND / BTEC National (lower)
-        15: "UPPER_SECONDARY",  # City & Guilds foundation
-        16: "POST_SECONDARY",  # RSA advanced
-        17: "TERTIARY",  # First/foundation degree
-        18: "TERTIARY",  # Second degree
-        19: "TERTIARY",  # Higher degree (Masters/PhD)
-        20: "TERTIARY",  # PGCE / teaching qualification
-        21: "TERTIARY",  # Nursing/paramedical qualification
-        66: "UPPER_SECONDARY",  # NVQ/SVQ Level 1
-        67: "UPPER_SECONDARY",  # NVQ/SVQ Level 2
-        68: "UPPER_SECONDARY",  # NVQ/SVQ Level 3
-        69: "POST_SECONDARY",  # NVQ/SVQ Level 4
-        70: "TERTIARY",  # NVQ/SVQ Level 5
+        12: "POST_SECONDARY",  # BTEC higher level
+        13: "POST_SECONDARY",  # SCOTVEC higher level
+        14: "POST_SECONDARY",  # NVQ/SVQ Level 4
+        15: "POST_SECONDARY",  # NVQ/SVQ Level 5
+        16: "POST_SECONDARY",  # RSA higher diploma / OCR Level 4
+        # A-level equivalent (UPPER_SECONDARY)
+        17: "UPPER_SECONDARY",  # A-Level or equivalent
+        18: "UPPER_SECONDARY",  # Welsh Baccalaureate Advanced
+        19: "UPPER_SECONDARY",  # Scottish Baccalaureate
+        20: "UPPER_SECONDARY",  # International Baccalaureate
+        21: "UPPER_SECONDARY",  # AS-level or equivalent
+        22: "UPPER_SECONDARY",  # Certificate of 6th Year Studies
+        23: "UPPER_SECONDARY",  # Access to Higher Education
+        24: "UPPER_SECONDARY",  # Scottish Higher/Intermediate
+        25: "UPPER_SECONDARY",  # Skills for work Higher
+        26: "POST_SECONDARY",  # ONC/OND
+        27: "POST_SECONDARY",  # BTEC National level
+        28: "POST_SECONDARY",  # SCOTVEC National level
+        29: "UPPER_SECONDARY",  # New Diploma Advanced
+        30: "UPPER_SECONDARY",  # New Diploma Progression
+        31: "UPPER_SECONDARY",  # NVQ/SVQ Level 3
+        32: "UPPER_SECONDARY",  # GNVQ Advanced
+        33: "UPPER_SECONDARY",  # RSA advanced diploma / OCR Level 3
+        34: "UPPER_SECONDARY",  # City and Guilds advanced craft
+        35: "UPPER_SECONDARY",  # Welsh Baccalaureate Intermediate
+        # GCSE/O-level equivalent (LOWER_SECONDARY)
+        36: "LOWER_SECONDARY",  # O-Level (5+)
+        37: "LOWER_SECONDARY",  # Scottish Standard Grade (5+)
+        38: "LOWER_SECONDARY",  # GCSE (5+)
+        39: "LOWER_SECONDARY",  # CSE (5+)
+        40: "LOWER_SECONDARY",  # Scottish National level 5
+        41: "LOWER_SECONDARY",  # Skills for work National 5
+        42: "LOWER_SECONDARY",  # BTEC first diploma
+        43: "LOWER_SECONDARY",  # SCOTVEC first diploma
+        44: "LOWER_SECONDARY",  # New Diploma Higher (level 2)
+        45: "LOWER_SECONDARY",  # NVQ/SVQ Level 2
+        46: "LOWER_SECONDARY",  # GNVQ Intermediate
+        47: "LOWER_SECONDARY",  # RSA diploma / OCR Level 2
+        48: "LOWER_SECONDARY",  # City and Guilds craft
+        49: "LOWER_SECONDARY",  # Other high school leavers qual
+        # Below GCSE / basic qualifications
+        50: "LOWER_SECONDARY",  # BTEC (unspecified)
+        51: "LOWER_SECONDARY",  # BTEC first cert
+        52: "LOWER_SECONDARY",  # SCOTVEC (unspecified)
+        53: "LOWER_SECONDARY",  # SCOTVEC first cert
+        54: "LOWER_SECONDARY",  # SCOTVEC modules
+        55: "LOWER_SECONDARY",  # New Diploma (unspecified)
+        56: "LOWER_SECONDARY",  # New Diploma Foundation
+        57: "LOWER_SECONDARY",  # Welsh Baccalaureate (unspecified)
+        58: "LOWER_SECONDARY",  # Welsh Baccalaureate Foundation
+        59: "LOWER_SECONDARY",  # NVQ/SVQ (unspecified)
+        60: "LOWER_SECONDARY",  # NVQ/SVQ Level 1
+        61: "LOWER_SECONDARY",  # GNVQ (unspecified)
+        62: "LOWER_SECONDARY",  # GNVQ Part One Intermediate
+        63: "LOWER_SECONDARY",  # GNVQ Full Foundation
+        64: "LOWER_SECONDARY",  # GNVQ Part One Foundation
+        65: "LOWER_SECONDARY",  # O-Level (unspecified)
+        66: "LOWER_SECONDARY",  # O-Level (fewer than 5)
+        67: "LOWER_SECONDARY",  # Scottish Standard Grade (unspecified)
+        68: "LOWER_SECONDARY",  # Scottish Standard Grade (fewer than 5)
+        69: "LOWER_SECONDARY",  # GCSE (unspecified)
+        70: "LOWER_SECONDARY",  # GCSE (fewer than 5)
+        71: "LOWER_SECONDARY",  # Scottish National 1-4
+        72: "LOWER_SECONDARY",  # Scottish National (unspecified)
+        73: "LOWER_SECONDARY",  # Skills for work National 3-4
+        74: "LOWER_SECONDARY",  # Skills for work (unspecified)
+        75: "LOWER_SECONDARY",  # CSE (unspecified)
+        76: "LOWER_SECONDARY",  # CSE (fewer than 5)
+        77: "LOWER_SECONDARY",  # RSA/OCR (unspecified)
+        78: "LOWER_SECONDARY",  # RSA other / OCR Level 1
+        79: "LOWER_SECONDARY",  # City and Guilds (unspecified)
+        80: "LOWER_SECONDARY",  # City and Guilds foundation
+        81: "LOWER_SECONDARY",  # YT Certificate
+        82: "LOWER_SECONDARY",  # Key Skills / Core Skills
+        83: "NOT_COMPLETED_PRIMARY",  # Basic Skills (literacy/numeracy)
+        84: "NOT_COMPLETED_PRIMARY",  # Entry Level Qualifications
+        85: "NOT_COMPLETED_PRIMARY",  # Award/Certificate at entry level
+        86: "LOWER_SECONDARY",  # Other professional/vocational/foreign
     }
-    # Codes 22-65 and 71-85 are further vocational/professional qualifications;
-    # treat as POST_SECONDARY. Codes 86-87 are catch-alls; treat as UPPER_SECONDARY.
-    for code in range(22, 66):
-        EDUCQUAL_MAP[code] = "POST_SECONDARY"
-    for code in range(71, 86):
-        EDUCQUAL_MAP[code] = "POST_SECONDARY"
-    EDUCQUAL_MAP[86] = "UPPER_SECONDARY"
-    EDUCQUAL_MAP[87] = "UPPER_SECONDARY"
+    # Code 87 is missing - means no qualification data; default to UPPER_SECONDARY
 
     educqual = pd.to_numeric(person.educqual, errors="coerce")
     pe_person["highest_education"] = educqual.map(EDUCQUAL_MAP).fillna(

policyengine_uk_data/datasets/imputations/student_loans.py

@@ -2,77 +2,185 @@
 Student loan plan imputation.
 
 This module imputes the student_loan_plan variable based on:
-- Whether the person has reported student loan repayments
+- Whether the person has reported student loan repayments (above threshold)
 - Their estimated university attendance year (inferred from age)
+- Probabilistic assignment for below-threshold borrowers
 
 The imputation assigns plan types according to when the loan system changed:
-- NONE: No reported repayments
+- NONE: No loan
 - PLAN_1: Started university before September 2012
 - PLAN_2: Started September 2012 - August 2023
 - PLAN_5: Started September 2023 onwards
 
-This enables policyengine-uk's student_loan_repayment variable to calculate
-repayments using official threshold parameters.
+The FRS only records active repayers (via PAYE). SLC data shows many borrowers
+earn below repayment thresholds (~55% of Plan 2 holders). This imputation
+fills that gap by probabilistically assigning plans to tertiary-educated
+people in the relevant age cohort without reported repayments, based on SLC
+"liable to repay" minus "above threshold" counts.
 """
 
 import numpy as np
 from policyengine_uk.data import UKSingleYearDataset
 from policyengine_uk import Microsimulation
 
+# England regions for filtering (SLC data covers England only)
+_ENGLAND_REGIONS = {
+    "NORTH_EAST",
+    "NORTH_WEST",
+    "YORKSHIRE",
+    "EAST_MIDLANDS",
+    "WEST_MIDLANDS",
+    "EAST_OF_ENGLAND",
+    "LONDON",
+    "SOUTH_EAST",
+    "SOUTH_WEST",
+}
+
+# SLC liable-to-repay counts (Higher Education total, England)
+# Source: https://explore-education-statistics.service.gov.uk/data-tables/permalink/6ff75517-7124-487c-cb4e-08de6eccf22d
+_PLAN_2_LIABLE = {
+    2025: 8_940_000,
+    2026: 9_710_000,
+    2027: 10_360_000,
+    2028: 10_615_000,
+    2029: 10_600_000,
+    2030: 10_525_000,
+}
+
+_PLAN_5_LIABLE = {
+    2025: 10_000,
+    2026: 230_000,
+    2027: 630_000,
+    2028: 1_380_000,
+    2029: 2_360_000,
+    2030: 3_400_000,
+}
+
+# SLC above-threshold counts (borrowers making repayments)
+_PLAN_2_ABOVE_THRESHOLD = {
+    2025: 3_985_000,
+    2026: 4_460_000,
+    2027: 4_825_000,
+    2028: 5_045_000,
+    2029: 5_160_000,
+    2030: 5_205_000,
+}
+
+_PLAN_5_ABOVE_THRESHOLD = {
+    2026: 35_000,
+    2027: 145_000,
+    2028: 390_000,
+    2029: 770_000,
+    2030: 1_235_000,
+}
+
 
 def impute_student_loan_plan(
     dataset: UKSingleYearDataset,
     year: int = 2025,
+    seed: int = 42,
 ) -> UKSingleYearDataset:
     """
-    Impute student loan plan type based on age and reported repayments.
+    Impute student loan plan type based on age, repayments, and education.
 
     The plan type determines which repayment threshold applies:
     - PLAN_1: £26,065 (2025), pre-Sept 2012 England/Wales
     - PLAN_2: £29,385 (2026-2029 frozen), Sept 2012 - Aug 2023
     - PLAN_4: Scottish loans (not imputed here - requires explicit flag)
     - PLAN_5: £25,000 (2025), Sept 2023 onwards
 
+    This function:
+    1. Assigns plans to people with reported repayments (above threshold)
+    2. Probabilistically assigns plans to tertiary-educated people without
+       repayments (below threshold) to match SLC liable-to-repay totals
+
     Args:
         dataset: PolicyEngine UK dataset with student_loan_repayments.
         year: The simulation year, used to estimate university attendance.
+        seed: Random seed for reproducibility.
 
     Returns:
         Dataset with imputed student_loan_plan values.
     """
     dataset = dataset.copy()
     sim = Microsimulation(dataset=dataset)
+    rng = np.random.default_rng(seed)
 
-    # Get required variables
     age = sim.calculate("age").values
-    student_loan_repayments = sim.calculate("student_loan_repayments").values
-
-    # Determine if person has a student loan based on reported repayments
-    has_student_loan = student_loan_repayments > 0
-
-    # Estimate when they started university (assume age 18)
-    # For simulation year Y and age A, university start year = Y - A + 18
-    estimated_uni_start_year = year - age + 18
+    repayments = sim.calculate("student_loan_repayments").values
+    region = sim.calculate("region", map_to="person").values
+    weights = sim.calculate("person_weight").values
+    education = sim.calculate("highest_education").values
+
+    is_england = np.isin(region, list(_ENGLAND_REGIONS))
+    is_tertiary = education == "TERTIARY"
+    has_repayments = repayments > 0
+
+    # Estimate university start year (assume started at 18)
+    uni_start_year = year - age + 18
+
+    # Age bands for plausible loan holders
+    # Plan 1: 32+ (started before 2012, graduated 21+ by 2015)
+    # Plan 2: 21-45 (allows for late starters, postgrads, career changers)
+    # Plan 5: 18-25 (recent starters only - cohort 2023+)
+    plan_1_age_mask = age >= 32
+    plan_2_age_mask = (age >= 21) & (age <= 45)
+    plan_5_age_mask = (age >= 18) & (age <= 25)
+
+    # Cohort masks based on university start year
+    plan_1_cohort = uni_start_year < 2012
+    plan_2_cohort = (uni_start_year >= 2012) & (uni_start_year < 2023)
+    plan_5_cohort = uni_start_year >= 2023
 
-    # Assign plan types based on when loan system changed
-    # StudentLoanPlan is a string enum: "NONE", "PLAN_1", "PLAN_2", "PLAN_4", "PLAN_5"
     plan = np.full(len(age), "NONE", dtype=object)
 
-    # Plan 1: Started before September 2012
-    plan_1_mask = has_student_loan & (estimated_uni_start_year < 2012)
-    plan[plan_1_mask] = "PLAN_1"
-
-    # Plan 2: Started September 2012 - August 2023
-    plan_2_mask = has_student_loan & (
-        (estimated_uni_start_year >= 2012) & (estimated_uni_start_year < 2023)
+    # Step 1: Assign plans to people with reported repayments
+    # Plan 1: use cohort (started before 2012)
+    # Plan 2: use age mask (21-45) since many late starters and postgrads exist
+    # Plan 5: use cohort (started 2023+)
+    plan[has_repayments & plan_1_cohort] = "PLAN_1"
+    plan[has_repayments & plan_2_age_mask & ~plan_1_cohort] = "PLAN_2"
+    plan[has_repayments & plan_5_cohort] = "PLAN_5"
+
+    # Step 2: Probabilistically assign below-threshold borrowers
+    # Only for tertiary-educated people in England without repayments
+    no_repayments = ~has_repayments
+
+    # Calculate target below-threshold counts
+    plan_2_below = _PLAN_2_LIABLE.get(year, 0) - _PLAN_2_ABOVE_THRESHOLD.get(
+        year, 0
+    )
+    plan_5_below = _PLAN_5_LIABLE.get(year, 0) - _PLAN_5_ABOVE_THRESHOLD.get(
+        year, 0
     )
-    plan[plan_2_mask] = "PLAN_2"
 
-    # Plan 5: Started September 2023 onwards
-    plan_5_mask = has_student_loan & (estimated_uni_start_year >= 2023)
-    plan[plan_5_mask] = "PLAN_5"
+    # Plan 2 below-threshold assignment
+    # Use age mask only (not cohort) since many borrowers started late or did postgrad
+    plan_2_eligible = (
+        no_repayments & is_tertiary & is_england & plan_2_age_mask
+    )
+    if plan_2_below > 0 and plan_2_eligible.sum() > 0:
+        eligible_weight = (weights * plan_2_eligible).sum()
+        if eligible_weight > 0:
+            prob = min(1.0, plan_2_below / eligible_weight)
+            draws = rng.random(len(age))
+            plan[plan_2_eligible & (draws < prob)] = "PLAN_2"
+
+    # Plan 5 below-threshold assignment
+    plan_5_eligible = (
+        no_repayments
+        & is_tertiary
+        & is_england
+        & plan_5_age_mask
+        & plan_5_cohort
+    )
+    if plan_5_below > 0 and plan_5_eligible.sum() > 0:
+        eligible_weight = (weights * plan_5_eligible).sum()
+        if eligible_weight > 0:
+            prob = min(1.0, plan_5_below / eligible_weight)
+            draws = rng.random(len(age))
+            plan[plan_5_eligible & (draws < prob)] = "PLAN_5"
 
-    # Store as the plan type
     dataset.person["student_loan_plan"] = plan
 
     return dataset

policyengine_uk_data/targets/build_loss_matrix.py

@@ -38,6 +38,7 @@
     compute_scotland_uc_child,
     compute_scottish_child_payment,
     compute_student_loan_plan,
+    compute_student_loan_plan_liable,
     compute_ss_contributions,
     compute_ss_headcount,
     compute_ss_it_relief,
@@ -306,8 +307,10 @@ def _compute_column(
         return compute_scottish_child_payment(target, ctx)
 
     # Student loan plan borrower counts (SLC)
-    if name.startswith("slc/plan_"):
+    if name.startswith("slc/plan_") and "above_threshold" in name:
         return compute_student_loan_plan(target, ctx)
+    if name.startswith("slc/plan_") and "liable" in name:
+        return compute_student_loan_plan_liable(target, ctx)
 
     # PIP claimants
     if name in (