8  Replicability & Reproducibility

# Mac/Linux use forward slashes /
/Users/giulia/Projects/thesis/          # Absolute path
data/raw/survey.csv                      # Relative path

# Navigate up one folder with ..
../other_project/data.csv               # Go up, then into other_project

# Home directory shortcut
~/Projects/thesis/                       # ~ means your home folder

* Check current working directory
pwd

* Set working directory (do this ONCE in master script)
cd "/Users/giulia/Projects/minimum-wage-study"

* Now all paths are relative to this location
use "data/raw/cps_2019.dta", clear
export delimited "data/processed/clean_data.csv"

/*==============================================================================
                    MASTER DO-FILE: Minimum Wage and Employment

    Paper:      "The Employment Effects of Minimum Wage Increases"
    Authors:    Smith, J. and Jones, M.
    Version:    1.0
    Date:       January 2025

    INSTRUCTIONS:
    1. Set the root path below to your project folder location
    2. Ensure all required packages are installed (see below)
    3. Run this entire file to reproduce all results

    REQUIRED PACKAGES: estout, reghdfe, ftools, coefplot
    Install with: ssc install estout, replace
================================================================================*/

clear all
set more off
cap log close

*------------------------------------------------------------------------------*
*  SET ROOT PATH - MODIFY THIS LINE ONLY
*------------------------------------------------------------------------------*
* Users should change this path to their own project folder location
if "`c(username)'" == "giulia" {
    global root "/Users/giulia/Projects/minimum-wage-study"
}
else if "`c(username)'" == "john" {
    global root "C:/Users/john/Research/minimum-wage-study"
}
else {
    * Default: assume current directory is project root
    global root "`c(pwd)'"
}

*------------------------------------------------------------------------------*
*  DEFINE FOLDER PATHS (do not modify)
*------------------------------------------------------------------------------*
global data     "$root/data"
global raw      "$data/raw"
global processed "$data/processed"
global code     "$root/code"
global output   "$root/output"
global tables   "$output/tables"
global figures  "$output/figures"
global logs     "$output/logs"

*------------------------------------------------------------------------------*
*  CREATE FOLDERS IF THEY DON'T EXIST
*------------------------------------------------------------------------------*
cap mkdir "$processed"
cap mkdir "$output"
cap mkdir "$tables"
cap mkdir "$figures"
cap mkdir "$logs"

*------------------------------------------------------------------------------*
*  START LOG FILE
*------------------------------------------------------------------------------*
local datetime: di %tcCCYY-NN-DD-HH-MM-SS Clock("`c(current_date)' `c(current_time)'","DMYhms")
log using "$logs/master_log_`datetime'.txt", text replace

di "=============================================="
di "  MASTER SCRIPT STARTED"
di "  Date/Time: `c(current_date)' `c(current_time)'"
di "  Stata version: `c(stata_version)'"
di "  Root directory: $root"
di "=============================================="

*------------------------------------------------------------------------------*
*  RUN ANALYSIS SCRIPTS IN ORDER
*------------------------------------------------------------------------------*
di _n ">>> Running 01_import_clean.do..."
do "$code/01_import_clean.do"

di _n ">>> Running 02_merge_construct.do..."
do "$code/02_merge_construct.do"

di _n ">>> Running 03_descriptive_stats.do..."
do "$code/03_descriptive_stats.do"

di _n ">>> Running 04_main_analysis.do..."
do "$code/04_main_analysis.do"

di _n ">>> Running 05_robustness.do..."
do "$code/05_robustness.do"

*------------------------------------------------------------------------------*
*  COMPLETION
*------------------------------------------------------------------------------*
di _n "=============================================="
di "  MASTER SCRIPT COMPLETED SUCCESSFULLY"
di "  End time: `c(current_date)' `c(current_time)'"
di "  All outputs saved to: $output"
di "=============================================="

log close

* Install the package (once)
ssc install estout, replace

* Run your regressions and store estimates
reg earnings education age, robust
estimates store m1

reg earnings education age experience, robust
estimates store m2

reg earnings education age experience i.industry, robust
estimates store m3

* Export to LaTeX
esttab m1 m2 m3 using "$tables/main_results.tex", ///
    replace                                        ///
    label                                          /// /// Use variable labels
    b(3) se(3)                                     /// /// 3 decimal places
    star(* 0.10 ** 0.05 *** 0.01)                 /// /// Significance stars
    title("Effect of Education on Earnings")       ///
    mtitles("Basic" "Controls" "Industry FE")      /// /// Column titles
    scalars("r2 R-squared" "N Observations")       ///
    nonotes                                        ///
    addnotes("Standard errors in parentheses."    ///
             "* p<0.10, ** p<0.05, *** p<0.01")

library(modelsummary)
library(fixest)

# Run regressions
m1 <- feols(earnings ~ education + age, data = df)
m2 <- feols(earnings ~ education + age + experience, data = df)
m3 <- feols(earnings ~ education + age + experience | industry, data = df)

# Export to LaTeX
modelsummary(
  list("Basic" = m1, "Controls" = m2, "Industry FE" = m3),
  output = here("output", "tables", "main_results.tex"),
  stars = c('*' = 0.10, '**' = 0.05, '***' = 0.01),
  coef_rename = c("education" = "Education (years)", "age" = "Age"),
  gof_omit = "AIC|BIC|Log",
  title = "Effect of Education on Earnings",
  notes = "Standard errors in parentheses."
)

from stargazer.stargazer import Stargazer
import statsmodels.api as sm

# Run regressions
X1 = sm.add_constant(df[['education', 'age']])
m1 = sm.OLS(df['earnings'], X1).fit(cov_type='HC1')

X2 = sm.add_constant(df[['education', 'age', 'experience']])
m2 = sm.OLS(df['earnings'], X2).fit(cov_type='HC1')

# Third model: add industry fixed effects via dummies
industry_dummies = pd.get_dummies(df['industry'], drop_first=True, dtype=int)
X3 = sm.add_constant(pd.concat([df[['education', 'age', 'experience']], industry_dummies], axis=1))
m3 = sm.OLS(df['earnings'], X3).fit(cov_type='HC1')

# Export to LaTeX
stargazer = Stargazer([m1, m2, m3])
stargazer.title("Effect of Education on Earnings")
stargazer.custom_columns(["Basic", "Controls", "Industry FE"])

with open(PATHS['tables'] / 'main_results.tex', 'w') as f:
    f.write(stargazer.render_latex())

\begin{table}[htbp]
\centering
\input{../output/tables/main_results.tex}
\end{table}

# modelsummary can export directly to a Word document
modelsummary(
  list("Basic" = m1, "Controls" = m2, "Industry FE" = m3),
  output = here("output", "tables", "main_results.docx"),
  stars = c('*' = 0.10, '**' = 0.05, '***' = 0.01)
)

# Makefile for research project
# Run with: make all

.PHONY: all clean data analysis paper

# Default target
all: paper

# Data processing (depends on raw data)
data/processed/clean_data.dta: data/raw/cps_2019.dta code/01_import_clean.do
	stata-mp -b do code/01_import_clean.do

# Analysis (depends on processed data)
output/tables/main_results.tex: data/processed/clean_data.dta code/04_main_analysis.do
	stata-mp -b do code/04_main_analysis.do

output/figures/figure1.pdf: data/processed/clean_data.dta code/04_main_analysis.do
	stata-mp -b do code/04_main_analysis.do

# Paper (depends on tables and figures)
paper/main.pdf: paper/main.tex output/tables/main_results.tex output/figures/figure1.pdf
	cd paper && pdflatex main.tex && bibtex main && pdflatex main.tex && pdflatex main.tex

paper: paper/main.pdf

# Clean all generated files
clean:
	rm -f data/processed/*.dta
	rm -f output/tables/*.tex
	rm -f output/figures/*.pdf
	rm -f paper/*.pdf paper/*.aux paper/*.log paper/*.bbl paper/*.blg

#!/bin/bash
# run_all.sh - Reproduce entire paper

echo "Starting full pipeline..."
echo "========================="

# Run Stata analysis
echo "Step 1: Running Stata analysis..."
stata-mp -b do code/00_master.do

# Run Python visualizations (if any)
echo "Step 2: Running Python scripts..."
python code/06_visualizations.py

# Compile LaTeX paper
echo "Step 3: Compiling paper..."
cd paper
pdflatex main.tex
bibtex main
pdflatex main.tex
pdflatex main.tex

echo "========================="
echo "Done! Paper saved to paper/main.pdf"

# After running your analysis pipeline
git add output/tables/*.tex output/figures/*.pdf
git commit -m "Update results"
git push

# Then in Overleaf: Menu → GitHub → Pull from GitHub

% main.tex - Master file for paper
\documentclass[12pt]{article}

% Load preamble (packages, settings, custom commands)
\input{preamble}

\title{The Employment Effects of Minimum Wage Increases}
\author{Jane Smith\thanks{University of Example. Email: jsmith@example.edu}}
\date{\today}

\begin{document}

\maketitle

\begin{abstract}
Your abstract here...
\end{abstract}

% Main content - each section in separate file
\input{sections/01_introduction}
\input{sections/02_literature}
\input{sections/03_data}
\input{sections/04_methodology}
\input{sections/05_results}
\input{sections/06_conclusion}

% Bibliography
\bibliographystyle{aer}
\bibliography{bibliography}

% Appendix
\appendix
\input{sections/appendix}

\end{document}

% preamble.tex - Packages and settings

% Essential packages
\usepackage[utf8]{inputenc}
\usepackage[T1]{fontenc}
\usepackage{amsmath,amssymb}
\usepackage{graphicx}
\usepackage{booktabs}        % Professional tables
\usepackage{natbib}          % Citations
\usepackage{hyperref}        % Clickable links
\usepackage{setspace}        % Line spacing
\usepackage[margin=1in]{geometry}

% For including Stata/R output tables
\usepackage{threeparttable}  % Table notes
\usepackage{tabularx}        % Flexible columns
\usepackage{siunitx}         % Number alignment

% Path to figures and tables (relative to main.tex)
\graphicspath{{../output/figures/}{figures/}}

% Custom commands for convenience
\newcommand{\tabpath}{../output/tables/}

% Double spacing for submission
\doublespacing

% In sections/05_results.tex

\section{Results}

Table \ref{tab:main} presents our main results...

\begin{table}[htbp]
\centering
\caption{Effect of Minimum Wage on Employment}
\label{tab:main}
\input{\tabpath main_results.tex}
\end{table}

The coefficient on minimum wage in column (3) suggests that...

# From the paper/ directory
cd paper

# Full compilation with bibliography
pdflatex main.tex       # First pass
bibtex main             # Process citations
pdflatex main.tex       # Resolve references
pdflatex main.tex       # Final pass

# Or use latexmk (handles everything automatically)
latexmk -pdf main.tex