build

Author: MaxGhenis

Makefile

@@ -1,4 +1,4 @@
-.PHONY: all format test install download upload docker documentation data clean build
+.PHONY: all format test install download upload docker documentation data clean build paper clean-paper
 
 all: data test
 
@@ -49,3 +49,15 @@ build:
 
 publish:
 	twine upload dist/*
+
+paper: paper/main.pdf
+
+paper/main.pdf: $(wildcard paper/sections/**/*.tex) $(wildcard paper/bibliography/*.bib) paper/main.tex paper/macros.tex
+	cd paper && \
+	TEXINPUTS=".:sections/methodology/:" pdflatex main && \
+	BSTINPUTS=".:bibliography/:" BIBINPUTS=".:bibliography/:" bibtex main && \
+	pdflatex main && \
+	pdflatex main
+
+clean-paper:
+	rm -f paper/*.aux paper/*.bbl paper/*.blg paper/*.log paper/*.out paper/*.toc paper/main.pdf paper/sections/**/*.aux

README.md

@@ -1 +1,50 @@
 # PolicyEngine US Data
+
+## Installation
+
+```bash
+pip install policyengine-us-data
+```
+
+## Building the Paper
+
+### Prerequisites
+
+The paper requires a LaTeX distribution (e.g., TeXLive or MiKTeX) with the following packages:
+
+- graphicx (for figures)
+- amsmath (for mathematical notation)
+- natbib (for bibliography management)
+- hyperref (for PDF links)
+- booktabs (for tables)
+- geometry (for page layout)
+- microtype (for typography)
+- xcolor (for colored links)
+
+On Ubuntu/Debian, you can install these with:
+
+```bash
+sudo apt-get install texlive-latex-base texlive-latex-recommended texlive-latex-extra texlive-fonts-recommended
+```
+
+On macOS with Homebrew:
+
+```bash
+brew install --cask mactex
+```
+
+### Building
+
+To build the paper:
+
+```bash
+make paper
+```
+
+To clean LaTeX build files:
+
+```bash
+make clean-paper
+```
+
+The output PDF will be at `paper/main.pdf`.

paper/bibliography/references.bib

@@ -121,4 +121,14 @@ @article{auerbach2018
   number  = {3},
   pages   = {541--576},
   year    = {2018}
+}
+
+@article{saez2012,
+  title   = {The Elasticity of Taxable Income with Respect to Marginal Tax Rates: A Critical Review},
+  author  = {Saez, Emmanuel and Slemrod, Joel and Giertz, Seth H},
+  journal = {Journal of Economic Literature},
+  volume  = {50},
+  number  = {1},
+  pages   = {3--50},
+  year    = {2012}
 }

paper/main.pdf

@@ -4,11 +4,27 @@
 \usepackage{amsmath}
 \usepackage{natbib}
 \usepackage{hyperref}
+\usepackage{booktabs}
+\usepackage{geometry}
+\usepackage{microtype}
+\usepackage{xcolor}
 
 \input{macros}
 
+\geometry{margin=1in}
+\hypersetup{
+    colorlinks=true,
+    linkcolor=blue,
+    filecolor=magenta,
+    urlcolor=blue,
+    citecolor=blue,
+}
+
 \title{Enhancing Survey Microdata with Administrative Records: \\ A Novel Approach to Microsimulation Dataset Construction}
-\author{PolicyEngine Team}
+\author{
+Nikhil Woodruff\thanks{PolicyEngine} \and
+Max Ghenis\thanks{PolicyEngine}
+}
 \date{\today}
 
 \begin{document}

paper/main.tex

@@ -1,4 +1,5 @@
-\section{Data}
+\section{Data}\label{sec:data}
+
 
 \subsection{Current Population Survey}
 

paper/sections/data.tex

@@ -0,0 +1,6 @@
+\section{Methodology}\label{sec:methodology}
+
+% Include methodology subsections
+\input{sections/methodology/overview}
+\input{sections/methodology/quantile_forests}
+\input{sections/methodology/reweighting}

paper/sections/methodology.tex

@@ -1,4 +1,4 @@
-\section{Quantile Regression Forests}
+\section{Quantile Regression Forests}\label{sec:qrf}
 
 We use quantile regression forests (QRF) in two distinct ways: direct imputation of missing variables, and generation of synthetic records.
 

paper/sections/methodology/quantile_forests.tex

@@ -1,4 +1,4 @@
-\section{Reweighting Procedure}
+\section{Reweighting Procedure}\label{sec:reweighting}
 
 Our reweighting process optimizes household weights to match administrative targets while determining the relative value of original CPS records versus PUF-derived synthetic records.
 
@@ -62,12 +62,12 @@ \subsection{Optimization Approach}
 
 \subsection{Implementation Details}
 
-From `enhanced_cps.py`:
+From \texttt{enhanced_cps.py}:
 \begin{itemize}
-    \item Learning rate: 0.1
-    \item Dropout rate: 5\%
-    \item Optimizer: Adam
-    \item Maximum iterations: 5,000
+\item Learning rate: 0.1
+\item Dropout rate: 5%
+\item Optimizer: Adam
+\item Maximum iterations: 5,000
 \end{itemize}
 
 % TODO: Add specific convergence metrics and typical runtime statistics