Merge pull request #460 from PolicyEngine/tob-calibrate

Add --use-tob flag for TOB revenue calibration

Author: baogorek

changelog_entry.yaml

@@ -0,0 +1,4 @@
+- bump: minor
+  changes:
+    added:
+    - Added --use-tob flag for TOB (Taxation of Benefits) revenue calibration targeting OASDI and HI trust fund revenue

policyengine_us_data/datasets/cps/long_term/README.md

@@ -6,8 +6,8 @@
 Run projections using `run_household_projection.py`:
 
 ```bash
-# Recommended: GREG with all three constraint types
-python run_household_projection.py 2100 --greg --use-ss --use-payroll --save-h5
+# Recommended: GREG with all constraint types
+python run_household_projection.py 2100 --greg --use-ss --use-payroll --use-tob --save-h5
 
 # IPF with only age distribution constraints (faster, less accurate)
 python run_household_projection.py 2050
@@ -21,6 +21,7 @@ python run_household_projection.py 2100 --greg --use-ss
 - `--greg`: Use GREG calibration instead of IPF
 - `--use-ss`: Include Social Security benefit totals as calibration target (requires `--greg`)
 - `--use-payroll`: Include taxable payroll totals as calibration target (requires `--greg`)
+- `--use-tob`: Include TOB (Taxation of Benefits) revenue as calibration target (requires `--greg`)
 - `--save-h5`: Save year-specific .h5 files to `./projected_datasets/` directory
 
 **Estimated runtime:** ~2 minutes/year without `--save-h5`, ~3 minutes/year with `--save-h5`
@@ -36,7 +37,7 @@ python run_household_projection.py 2100 --greg --use-ss
 
 **GREG (Generalized Regression Estimator)**
 - Solves for weights matching multiple constraints simultaneously
-- Can enforce age distribution + Social Security benefits + taxable payroll
+- Can enforce age distribution + Social Security benefits + taxable payroll + TOB revenue
 - One-shot solution using `samplics` package
 - **Recommended** for accurate long-term projections
 
@@ -57,17 +58,29 @@ python run_household_projection.py 2100 --greg --use-ss
    - Calculated as: `taxable_earnings_for_social_security` + `social_security_taxable_self_employment_income`
    - Source: SSA Trustee Report 2024 (`social_security_aux.csv`)
 
+4. **TOB Revenue** (`--use-tob`, GREG only)
+   - Taxation of Benefits revenue for OASDI and Medicare HI trust funds
+   - OASDI: `tob_revenue_oasdi` (tier 1 taxation, 0-50% of benefits)
+   - HI: `tob_revenue_medicare_hi` (tier 2 taxation, 50-85% of benefits)
+   - Source: SSA Trustee Report 2024 (`social_security_aux.csv`)
+
 ---
 
 ### Data Sources
 
-All data from **SSA 2024 Trustee Report**:
+**SSA 2025 OASDI Trustees Report**
+- URL: https://www.ssa.gov/OACT/TR/2025/
+- File: `SingleYearTRTables_TR2025.xlsx`
+- Tables: IV.B2 (OASDI TOB % of taxable payroll), VI.G6 (taxable payroll in billions), VI.G9 (OASDI costs)
 
-- `SSPopJul_TR2024.csv` - Population projections 2025-2100 by single year of age
-- `social_security_aux.csv` - OASDI costs and taxable payroll projections 2025-2100
-  - Extracted from `SingleYearTRTables_TR2025.xlsx` Table VI.G9 using `extract_ssa_costs.py`
+**CMS 2025 Medicare Trustees Report**
+- URL: https://www.cms.gov/data-research/statistics-trends-and-reports/trustees-report-trust-funds
+- File: `tr2025-tables-figures.zip` → CSV folder → "Medicare Sources of Non-Interest Income..."
+- Column: Tax on Benefits (values in millions, 2024-2099)
 
-Files located in: `policyengine_us_data/storage/`
+**Local files** (in `policyengine_us_data/storage/`):
+- `SSPopJul_TR2024.csv` - Population projections 2025-2100 by single year of age
+- `social_security_aux.csv` - OASDI costs, taxable payroll, and TOB revenue projections 2025-2100
 
 ---
 

policyengine_us_data/datasets/cps/long_term/calibration.py

@@ -85,6 +85,10 @@ def calibrate_greg(
     payroll_target=None,
     h6_income_values=None,
     h6_revenue_target=None,
+    oasdi_tob_values=None,
+    oasdi_tob_target=None,
+    hi_tob_values=None,
+    hi_tob_target=None,
     n_ages=86,
 ):
     """
@@ -101,6 +105,10 @@ def calibrate_greg(
         payroll_target: Optional taxable payroll target total
         h6_income_values: Optional H6 reform income values per household
         h6_revenue_target: Optional H6 reform total revenue impact target
+        oasdi_tob_values: Optional OASDI TOB revenue values per household
+        oasdi_tob_target: Optional OASDI TOB revenue target total
+        hi_tob_values: Optional HI TOB revenue values per household
+        hi_tob_target: Optional HI TOB revenue target total
         n_ages: Number of age groups
 
     Returns:
@@ -116,6 +124,8 @@ def calibrate_greg(
         (ss_values is not None and ss_target is not None)
         or (payroll_values is not None and payroll_target is not None)
         or (h6_income_values is not None and h6_revenue_target is not None)
+        or (oasdi_tob_values is not None and oasdi_tob_target is not None)
+        or (hi_tob_values is not None and hi_tob_target is not None)
     )
 
     if needs_aux_df:
@@ -135,6 +145,14 @@ def calibrate_greg(
             aux_df["h6_revenue"] = h6_income_values
             controls["h6_revenue"] = h6_revenue_target
 
+        if oasdi_tob_values is not None and oasdi_tob_target is not None:
+            aux_df["oasdi_tob"] = oasdi_tob_values
+            controls["oasdi_tob"] = oasdi_tob_target
+
+        if hi_tob_values is not None and hi_tob_target is not None:
+            aux_df["hi_tob"] = hi_tob_values
+            controls["hi_tob"] = hi_tob_target
+
         aux_vars = aux_df
     else:
         aux_vars = X
@@ -160,6 +178,10 @@ def calibrate_weights(
     payroll_target=None,
     h6_income_values=None,
     h6_revenue_target=None,
+    oasdi_tob_values=None,
+    oasdi_tob_target=None,
+    hi_tob_values=None,
+    hi_tob_target=None,
     n_ages=86,
     max_iters=100,
     tol=1e-6,
@@ -180,6 +202,10 @@ def calibrate_weights(
         payroll_target: Optional payroll target (for GREG with payroll)
         h6_income_values: Optional H6 reform income values per household
         h6_revenue_target: Optional H6 reform total revenue impact target
+        oasdi_tob_values: Optional OASDI TOB revenue values per household
+        oasdi_tob_target: Optional OASDI TOB revenue target total
+        hi_tob_values: Optional HI TOB revenue values per household
+        hi_tob_target: Optional HI TOB revenue target total
         n_ages: Number of age groups
         max_iters: Max iterations for IPF
         tol: Convergence tolerance for IPF
@@ -204,6 +230,10 @@ def calibrate_weights(
                 payroll_target,
                 h6_income_values,
                 h6_revenue_target,
+                oasdi_tob_values,
+                oasdi_tob_target,
+                hi_tob_values,
+                hi_tob_target,
                 n_ages,
             )
         except Exception as e: