Distributional Analysis

---
name: distributional-analysis
description: "Analyzes distributional effects of a policy or shock using microsimulation, HANK links or survey-based incidence."
---
<!-- Generated from .claude/skills/distributional-analysis/SKILL.md by tools/sync_agents.py. Edit the source, then run the script. -->

# /distributional-analysis — Distributional Analysis

**Category:** Analysis · **Primary agent:** `inequality-distribution-specialist`

Analyzes distributional effects of a policy or shock using microsimulation, HANK links or survey-based incidence.

Arguments: whatever the user wrote after the command name.

## Purpose
Analyze how a policy or shock affects different households: who gains, who loses, by how much, and what happens to poverty and inequality. Macro or sector results are mapped to households through income, price and employment channels, using microsimulation, survey-based incidence or links to heterogeneous-agent models. The output reports results with sampling uncertainty and costs compensation options.

**Use it when** tax, subsidy, transfer, carbon-pricing, inflation or other shocks have distributional consequences that matter for the decision.

**Do not use it when** a full heterogeneous-agent macro model is required for transmission (`/build-hank`).

## Before you start
1. **Check required inputs.** For each input below record `FOUND` or `ABSENT` (never 'assumed'):
   - Household survey data
   - Macro scenario
   If a required input is `ABSENT`, that part is **`NOT ASSESSED — NO DATA`**: do not estimate or invent it; name what is missing and which skill produces it. If all required inputs are absent, stop and say so.
2. **Check confidentiality.** Identify the data classification level of the inputs (`.claude/docs/confidentiality-and-ai-use.md`). Do not proceed with restricted or confidential data in a way the policy does not allow.
3. **Collaboration.** Follow `.claude/docs/collaboration-protocol.md`: ask questions first, present options, get approval before writing files, and update `production/session-state/active.md` after each approved section.

## Agents
- `inequality-distribution-specialist` — primary agent; coordinates the work and integrates results
- `tax-benefit-microsimulation-specialist` — Builds tax-benefit microsimulation
- `hank-specialist` — Builds heterogeneous-agent (HANK) models
- `survey-microdata-specialist` — Works with household and firm survey microdata

Each agent is defined in `.claude/agents/<name>.md`. If your tool runs subagents, run these agents as subagents, in parallel where the steps are independent; otherwise read each agent's file and apply its instructions in turn. Subagents only write to the paths named in your instructions.

## Key design decisions (present options, let the user choose)
| Decision | Typical options | What it changes |
|---|---|---|
| Welfare measure | income, consumption, real purchasing power | Ranking of households |
| Method | static incidence, behavioral microsimulation, macro–micro link, HANK | Channels captured |
| Groups | deciles, regions, urban/rural, gender, household type | What is reported |
| Poverty line | national, international, relative | Poverty results |

## Workflow
1. Define groups and welfare measure (income, consumption, real purchasing power)
2. Map macro changes to households; include price and employment channels
   - Use consumption baskets for price effects; income sources for wage and transfer effects
3. Compute winners/losers, poverty and inequality changes with sampling uncertainty
   - Design-based standard errors; sensitivity to the poverty line
4. Propose compensation or mitigation options and their cost
   - Targeting performance: coverage and leakage

## Checkpoints with the user
- After defining groups and welfare: confirm before computation
- After results: confirm compensation options to cost

## Common pitfalls
- Ignoring survey design in standard errors
- Averages that hide large losses for some groups
- Assuming full take-up of compensation
- Ignoring under-coverage of top incomes

## Output
`forecasts/distribution/<name>.md`

The report presents the method, groups, winners and losers, poverty and inequality effects with uncertainty, and compensation options with costs.

## Gate / verdict
- Sampling uncertainty reported
- Gains and losses are shown separately
- Compensation options are costed

## Suggested next steps
- `/policy-brief`
- `/chart-pack`