Empirical Finance from the Ground Up — ASSIP 2026 Cohort
Home
Front Matter
Weeks
Week 1 — Probability & Inference
Week 2 — OLS & Inference
Week 3 — Causal Inference
Week 4 — Quasi-Experiments
Week 5 — Reading Finance Papers
Week 6 — Text, AI, Alt Data
Week 7 — Your Project I
Week 8 — Your Project II
Capstones
Instructor Manual
Assignments
Cohort Projects
About
Twitter
LinkedIn
Appendices
Appendix B — Python & LaTeX Setup
Appendix B — Python + LaTeX Setup (stub). See ../../TOC.md.
Empirical Finance from the Ground Up — ASSIP 2026 Cohort
Front Matter
Preface
Articulation Matrix: The 8-Week Camp and the ASSIP 2026 Calendar
How to Use This Book
Prerequisite Self-Test
The Cohort and the Mentorship Structure
Table of Contents —
Empirical Finance from the Ground Up
Week 1 — Probability, Inference, and the Logic of Estimation
Week 1 — Probability, Sampling, and the Logic of Inference
Ch 1.1 — Joint, Conditional, and the Two Laws That Run Everything
Ch 1.2 — Expectations, Variance, Covariance as Geometry
Chapter 1.3 — Estimators and Their Sampling Distributions
Ch 1.4 — The LLN and the CLT, Shown Not Asserted
Chapter 1.5 — Hypothesis Testing Done Right
Lab 1 — Build a Coin-Flip Universe
Mentor Session 1 — “What Is a Finding?”
PS 1.1 — Conditional Probability & LIE/LTV Drills
PS 1.2 — Expectation/Variance Algebra & Correlation Geometry
Problem Set 1.3 — Bias, Variance, and MSE of Estimators
Problem Set 1.4 — The LLN and the CLT, by Hand and by Simulation
Problem Set 1.5 — Power, Size, and Confidence Intervals
Week 1 Assessment — Probability, Estimation, and Inference
nb1.1 — LIE / LTV by Simulation
nb1.2 — Covariance Matrices & Correlation Heatmaps
nb1.3 — The Sampling-Distribution Explorer
nb1.4 — The LLN and the CLT, Shown Not Asserted
Notebook 1.5 — Power Curves and the t-Test From Scratch
Week 2 — OLS, Geometry, and Inference
Week 2 — The OLS Engine
Ch 2.1 — OLS in Matrix Form
Chapter 2.2 — Gauss–Markov and the Meaning of “Best”
Ch 2.3 — The Frisch–Waugh–Lovell Theorem
Chapter 2.4 — When the Errors Misbehave: Heteroskedasticity, Clustering, HC/HAC
Chapter 2.5 — Misspecification: OVB, Measurement Error, Functional Form
Lab 2 — Replicate a Textbook Fama–MacBeth on CRSP
Mentor Session 2 — “Why your standard error is the whole ballgame.”
PS 2.1 — Matrix-OLS Derivations & Numerical Inversion
PS 2.2 — Gauss–Markov: Breaking the Contract on Purpose
PS 2.3 — Frisch–Waugh–Lovell: Partialling-Out by Hand
Problem Set 2.4 — Robust, Clustered, and HAC Standard Errors
Problem Set 2.5 — OVB Sign Predictions and the Measurement-Error Simulation
Week 2 Assessment — The OLS Engine
nb2.1 — OLS from Scratch with NumPy vs. statsmodels
nb2.2 — Gauss–Markov by Monte Carlo: Seeing “BLUE”
nb2.3 — FWL Residualization, Visualized
Notebook 2.4 — Standard-Error Flavors on a Clustered Panel
nb2.5 — The Biased-Estimator Lab
Week 3 — Causal Inference Foundations
Week 3 — Causal Inference I: Potential Outcomes, Selection-on-Observables, and Instruments
Chapter 3.1 — Potential Outcomes, SUTVA, and the Fundamental Problem of Causal Inference
Chapter 3.2 — Selection on Observables I: Matching & Propensity Scores
Chapter 3.3 — Selection on Observables II: Entropy Balancing & Doubly-Robust Estimation
Ch 3.4 — Instrumental Variables
Chapter 3.5 — Reading IV in the Wild + The Weak-IV Pathology
Lab 3 — Reproduce a Weak-IV Pathology
Mentor Session 3 — “Natural experiments: finding the lever nature pulled.”
PS 3.1 — Potential-Outcomes Algebra & the Selection-Bias Decomposition
Problem Set 3.2 — Hand-Matching, Propensity Scores, and the Limits of Selection-on-Observables
PS 3.3 — Entropy-Balancing Weights & AIPW by Hand
Problem Set 3.4 — Instrumental Variables: 2SLS Derivation and Weak-IV Diagnostics
Problem Set 3.5 — Anderson–Rubin Inference and the Instrument-Validity Critique
Week 3 Assessment — Causal Inference I
nb3.1 — Potential Outcomes & Selection Bias: Playing God with the Science Table
nb3.2 — Propensity-Score Matching with Balance Diagnostics
Notebook 3.3 — Entropy Balancing vs. IPW vs. AIPW
nb3.4 — 2SLS with
linearmodels
; the First-Stage F
nb3.5 — The Weak-Instrument Pathology, Reproduced
Week 4 — Quasi-Experiments in Finance
Week 4 — Causal Inference II: DiD, RD, Synthetic Control, and Shift-Share
Chapter 4.1 — Difference-in-Differences and Event Studies
Ch 4.2 — The Staggered-Adoption Crisis
Ch 4.3 — Regression Discontinuity
Ch 4.4 — Synthetic Control & Synthetic DiD
Ch 4.5 — Bartik / Shift-Share Designs
Lab 4 — A Clean DiD on HMDA + a State Policy Shock
Mentor Session 4 — “Detecting discrimination with a clean design.”
PS 4.1 — The 2×2 Difference-in-Differences and Event-Study Construction
Problem Set 4.2 — Goodman-Bacon by Hand, and the Negative-Weights Crisis
Problem Set 4.3 — Regression Discontinuity: Local-Polynomial Fitting and Bandwidth Experiments
PS 4.4 — Synthetic Control Weights & Placebo Inference
Problem Set 4.5 — Shift-Share Exposure Weights and the Identification Critique
Week 4 Assessment — Causal Inference II
nb4.1 — Event Studies & Parallel Trends: Playing God with Priya's Climate-Insurance Shock
nb4.2 — Staggered DiD: TWFE vs. Callaway–Sant’Anna
nb4.3 — RD with
rdrobust
; CCT bandwidths
nb4.4 — Synthetic Control & Synthetic DiD: Building the Counterfactual You Wish You Had
nb4.5 — Bartik / Shift-Share Instrument Decomposition
Week 5 — Reading the Empirical Finance Canon
Week 5 — Reading the Frontier I: Decoding Empirical Papers
Chapter 5.1 — Reader's Guide: *The Cross-Section of Expected Stock Returns* (Fama & French 1992)
Ch 5.2 — Reader's Guide: Fama & French (1993), "Common Risk Factors in the Returns on Stocks and Bonds"
Ch 5.3 — Reader's Guide: Jegadeesh & Titman (1993)
Chapter 5.4 — Reader’s Guide: Petersen (2009), “Estimating Standard Errors in Finance Panel Data Sets”
Chapter 5.5 — Reader's Guide: Bertrand, Duflo & Mullainathan (2004)
Reading Guide Pack 5 — How to Read an Empirical Paper
Mentor Session 5 — “Anatomy of a JF paper.”
PS 5.1 — Sorting, Double-Sorting, and the Fama–MacBeth Horse Race in Fama & French (1992)
Problem Set 5.2 — FF93 Factor Construction & Time-Series Regressions
PS 5.3 — Momentum Portfolio Replication and the Transaction-Cost Critique
Problem Set 5.4 — Re-running Petersen’s Clustering Comparison on a Panel
Problem Set 5.5 — Reproduce a BDM Placebo-DiD False Positive
Week 5 Assessment — Reading the Frontier I
nb5.1 — FF92 Portfolio Sorts: the Size and Book-to-Market Cross-Section
nb5.2 — FF93 Factor Regressions: Loadings,
R^2
,
\alpha
, and the GRS Test
Notebook 5.3 — Momentum Backtest (Jegadeesh–Titman)
Notebook 5.4 — Replicating Petersen (2009): The Clustering Taxonomy
nb5.5 — The BDM Placebo-Law Simulation
Week 6 — Text, AI, and Alternative Data
Week 6 — Reading the Frontier II: Text, Modern Empirics, and the AI Co-Pilot
Chapter 6.1 — Reader's Guide: *Technological Innovation, Resource Allocation, and Growth* (Kogan, Papanikolaou, Seru & Stoffman 2017)
Chapter 6.2 — Reader's Guide: Hoberg & Phillips (2016), "Text-Based Network Industries and Endogenous Product Differentiation"
Chapter 6.3 — Reader's Guide: Loughran & McDonald (2011), "When Is a Liability Not a Liability?"
Chapter 6.4 — Reader's Guide: Fair Lending in the Algorithmic Era (Bartlett et al. 2022; Bhutta, Hizmo & Ringo)
Chapter 6.5 — The AI Co-Pilot for Research (LLM-in-the-Loop)
Reading Guide Pack 6 + AI Lab Manual — When the Data Is Words, and the Tool Has Opinions
Mentor Session 6 — “Text as data, and AI without fooling yourself.”
PS 6.1 — Building the KPSS Patent-Value Measure: Construction, Validation, and Critique
Problem Set 6.2 — 10-K Cosine Similarity & TNIC Mini-Build
PS 6.3 — The LM Dictionary vs. a Naive Dictionary: When a Liability Is Not a Liability
Problem Set 6.4 — Fair-Lending Decomposition and the Disparate-Impact Critique
Problem Set 6.5 — An LLM Classifier as a Measurement Instrument: Held-Out Validation and a Leakage Audit
Week 6 Assessment — Reading the Frontier II: Build and Validate a Text Classifier
nb6.1 — Building a Patent-Value Panel: Reading a Patent’s Worth Off the Stock Price (KPSS-style)
nb6.2 — 10-K Text Vectorization & Similarity (Hoberg–Phillips, TNIC-style)
nb6.3 — The Loughran–McDonald Sentiment Pipeline
nb6.4 — Mortgage-Disparity Decomposition: How Much of Maya’s Gap Is Real Risk?
nb6.5 — The AI Co-Pilot Lab
Week 7 — Your Project, Part I
Week 7 — Independent Research Project I: From Question to Pre-Analysis Plan
Chapter 7.1 — Idea-Generation Workshop
Chapter 7.2 — Data Acquisition in Practice
Chapter 7.3 — The Pre-Analysis Plan (Short Form)
Chapter 7.4 — Building the Analysis Dataset
Ch 7.5 — The Identification Memo
Lab 7 — Your Data, Reproducibly
Mentor Session 7 — “How I pick a project — and kill one.”
PS 7.1 — Three Candidate Questions, Scored: A Feasibility-and-Novelty Deliverable
PS 7.2 — A Working Data-Pull Script and Data Card for One Project Source
PS 7.3 — Write and Register a Complete Pre-Analysis Plan for
Your
Project
PS 7.4 — A Reproducible Merged Analysis Dataset, With Diagnostics
PS 7.5 — Your Identification Memo + Threats Table
Week 7 Assessment — Independent Research Project I: The Design Half
nb7.1 — The Idea-to-Spec Template
nb7.2 — The Multi-Source Data-Pull Harness
Notebook 7.3 — PAP Companion: A Power Calculation for
Your
Design
nb7.4 — Building the Analysis Dataset: Merge, Lag, and Validate
nb7.5 — First-Look Regressions: Frozen Until the PAP Is Filed
Week 8 — Your Project, Part II
Week 8 — Independent Research Project II: Execution, Robustness, Poster, and Defense
Chapter 8.1 — Execution & the Specification Curve
Ch 8.2 — Robustness & Inference Stress-Tests
Chapter 8.3 — Writing the Empirical Paper (and the Abstract Your Poster Carries)
Ch 8.4 — Peer Review & Revision
Ch 8.5 — The 8-Minute Poster Talk & the Replication Packet
Lab 8 — Final Poster + Repo + Symposium Defense
Mentor Session 8 — “Defending a result: what a referee actually asks.”
PS 8.1 — Specification Curve for Your Main Result
PS 8.2 — The Full Robustness Battery + Write-Up
PS 8.3 — Draft Your JSSR Abstract and Poster Results Narrative Against the Style Guide
PS 8.4 — A Referee Report + Your R&R Memo
PS 8.5 — Your 8-Minute Poster Talk + the One-Click Replication Packet
Week 8 Assessment — The Capstone (Terminal Assessment of ASSIP)
nb8.1 — The Specification-Curve Generator
nb8.2 — The Robustness Battery: Try to Kill Your Own Result
nb8.3 — Publication-Quality Tables & Figures: Turning Maya's Frozen Results into a Paper
nb8.4 — The Reproducibility Check: Can a Stranger Regenerate Your Number?
nb8.5 — The Final Manuscript Build: Markdown/LaTeX → PDF
Capstone Projects
Capstone Gallery — Exemplar Papers Behind the ASSIP Poster Deliverable
Capstone 1 (Exemplar) — Fair Lending on HMDA: How Much of the Mortgage-Denial Gap Survives the Controls?
Capstone 2 (Exemplar) — Common Ownership from 13F
Capstone 3 — Innovation from USPTO PatentsView
Capstone 4 — Reading the Tape: An Out-of-Sample-Validated Text Classifier for SEC 8-K Events and the Short-Window Return Reaction
Capstone 5 — FRED Macro Event Study
Instructor Manual
Instructor’s Manual — ASSIP 2026
IM-1 — Pacing Guide
IM-2 — Grading Rubrics (Consolidated)
IM-3 — Common Student Pitfalls, by Week
IM-4 — Mentor-Session Facilitation & Guest Lectures
IM-5 — Answer Keys & Anchor Work
IM-6 — Equity, Access & Compliance
Appendices
Appendix A — Math Toolkit
Appendix A — Math Toolkit (stub). See ../../TOC.md.
A.1 — Matrix Algebra (just enough)
A.2 — Optimization (just enough)
A.3 Asymptotics
A.4 Probability Distributions Reference
Appendix B — Python & LaTeX Setup
Appendix B — Python + LaTeX Setup (stub). See ../../TOC.md.
B.1 Toolchain
B.2 GitHub & GitHub Classroom
B.3 WRDS Cloud
B.4 — GMU Hopper SLURM
B.5 — Overleaf + the AEA LaTeX Template
Appendix C — Data Dictionary
Appendix C — Data Dictionary Master
Data Cards — Appendix C source dictionary
Data Card — U.S. Bureau of Economic Analysis (BEA)
Data Card — U.S. Bureau of Labor Statistics (BLS)
Data Card — Capital IQ (S&P Capital IQ via WRDS)
Data Card — U.S. Census Bureau: ACS + County Business Patterns
Data Card — CFPB Consumer Complaint Database
Data Card — Compustat (S&P Global Fundamentals)
Data Card — CRSP (Center for Research in Security Prices)
Data Card — Crypto / On-Chain: Etherscan / CoinGecko / DeFiLlama
Data Card — SEC EDGAR 10-K / 10-Q (Annual & Quarterly Reports)
Data Card — SEC EDGAR 13F (Institutional Holdings, the Free Path)
Data Card — SEC EDGAR 8-K (Material Events)
Data Card — SEC EDGAR DEF 14A (Proxy Statements)
Data Card — SEC EDGAR N-PORT (Fund Portfolio Holdings)
Data Card — FDIC (Institution Directory, SDI financials, and bank failures)
Data Card — Call Reports (FFIEC)
Data Card — FOMC Text (statements / minutes / speeches) + GDELT Global News
Data Card — FR Y-9C (Bank Holding Company Financials)
Data Card — FRED (Federal Reserve Economic Data)
Data Card — Free Equity Price APIs: yfinance / Stooq / Tiingo / Alpha Vantage
Data Card — HMDA (Home Mortgage Disclosure Act Loan Application Register)
Data Card — IBES (Institutional Brokers’ Estimate System)
Data Card — International Macro: ECB SDW · BIS · IMF IFS · World Bank WDI · OECD.Stat
Data Card — Loughran–McDonald Master Dictionary (Finance Sentiment Word Lists)
Data Card — Mergent FISD (Fixed Income Securities Database)
Data Card — MSRB EMMA (Municipal securities disclosures and trades)
Data Card — NBER / KPSS Patent–Compustat Links
Data Card — NOAA Billion-Dollar Disasters / Storm Events + FEMA Disaster Declarations
Data Card — OptionMetrics (IvyDB US)
Data Card — Thomson Reuters / SEC 13F Institutional Holdings
Data Card — TRACE (Transaction Reporting and Compliance Engine)
Data Card — U.S. Treasury (TreasuryDirect + Daily Yield Curve) and FINRA TRACE
Data Card — USAspending.gov (Federal Awards)
Data Card — USPTO PatentsView (now USPTO Open Data Portal)
Appendix D — Style Guide
Appendix D — Empirical-Finance Style Guide (stub). See ../../TOC.md.
D.1 — Table Craft
D.2 — Reporting Regressions
D.3 — Robustness Sections That Persuade
D.4 — The Replication Packet Standard
D.5 — Prose Style
Appendix E — Solutions Manual
Appendix E — Solutions Manual
Solutions — PS 1.1 (Conditional Probability & LIE/LTV Drills)
Solutions — PS 1.2 (Expectation/Variance Algebra & Correlation Geometry)
Solutions — Problem Set 1.3 (Bias, Variance, and MSE of Estimators)
Solutions — Problem Set 1.4 (The LLN and the CLT)
Solutions — Problem Set 1.5 (Power, Size, and Confidence Intervals)
Solutions — PS 2.1 (Matrix-OLS Derivations & Numerical Inversion)
Solutions — PS 2.2 (Gauss–Markov: Breaking the Contract on Purpose)
Solutions — PS 2.3 (Frisch–Waugh–Lovell: Partialling-Out by Hand)
Solutions — Problem Set 2.4 (Robust, Clustered, and HAC Standard Errors)
Solutions — Problem Set 2.5 (OVB Sign Predictions and the Measurement-Error Simulation)
Solutions — PS 3.1 (Potential-Outcomes Algebra & the Selection-Bias Decomposition)
Solutions — Problem Set 3.2 (Hand-Matching, Propensity Scores, and the Limits of Selection-on-Observables)
Solutions — PS 3.3 (Entropy-Balancing Weights & AIPW by Hand)
Solutions — Problem Set 3.4 (Instrumental Variables: 2SLS Derivation and Weak-IV Diagnostics)
Solutions — Problem Set 3.5 (Anderson–Rubin Inference and the Instrument-Validity Critique)
Solutions — PS 4.1 (The 2×2 Difference-in-Differences and Event-Study Construction)
Solutions — Problem Set 4.2 (Goodman-Bacon by Hand, and the Negative-Weights Crisis)
Solutions — Problem Set 4.3 (Regression Discontinuity: Local-Polynomial Fitting and Bandwidth Experiments)
Solutions — PS 4.4 (Synthetic Control Weights & Placebo Inference)
Solutions — Problem Set 4.5 (Shift-Share Exposure Weights and the Identification Critique)
Solutions — PS 5.1 (Sorting, Double-Sorting, and the Fama–MacBeth Horse Race in Fama & French 1992)
Solutions — Problem Set 5.2 (FF93 Factor Construction & Time-Series Regressions)
Solutions — PS 5.3 (Momentum Portfolio Replication and the Transaction-Cost Critique)
Solutions — Problem Set 5.4 (Re-running Petersen’s Clustering Comparison on a Panel)
Solutions — Problem Set 5.5 (Reproduce a BDM Placebo-DiD False Positive)
Solutions — PS 6.1 (Building the KPSS Patent-Value Measure: Construction, Validation, and Critique)
Solutions — Problem Set 6.2 (10-K Cosine Similarity & TNIC Mini-Build)
Solutions — PS 6.3 (The LM Dictionary vs. a Naive Dictionary: When a Liability Is Not a Liability)
Solutions — Problem Set 6.4 (Fair-Lending Decomposition and the Disparate-Impact Critique)
Solutions — Problem Set 6.5 (An LLM Classifier as a Measurement Instrument: Held-Out Validation and a Leakage Audit)
Model Deliverable — PS 7.1 (Three Candidate Questions, Scored)
Solutions — PS 7.2 (A Working Data-Pull Script and Data Card for One Project Source)
Model Deliverable — PS 7.3 (A Complete Pre-Analysis Plan Draft)
Solutions — PS 7.4 (A Reproducible Merged Analysis Dataset, With Diagnostics)
Model Deliverable — PS 7.5 (Identification Memo + Threats Table)
Model Deliverable — PS 8.1 (Specification Curve for Your Main Result)
Model Deliverable — PS 8.2 (The Full Robustness Battery + Write-Up)
Model Deliverable — PS 8.3 (An A-Grade Introduction + Headline-First Results Excerpt)
Model Deliverable — PS 8.4 (Referee Report + R&R Memo)
Model Deliverable — PS 8.5 (8-Minute Deck + One-Click Replication Packet)
ASSIP 2026 Cohort
Assignments
Week of July 10 — AI and the Labor Market, and Reading a Finance Paper
Cohort Research Projects
Appendices
Appendix B — Python & LaTeX Setup
Appendix B — Python + LaTeX Setup (stub). See ../../TOC.md.
Appendix F — Appendix B — Python + LaTeX Setup (stub). See ../../TOC.md.
Code
A.4 Probability Distributions Reference
B.1 Toolchain
Source Code
# Appendix B — Python + LaTeX Setup (stub). See ../../TOC.md.