Introduction

In this assignment, you will demonstrate your ability to understand and conduct a difference-in-differences analysis by replicating part of the main analysis from the article “When Migrants Mobilize Against Labor Exploitation” (Gemma Dipoppa, American Political Science Review, 2025).

Abstract

Formalities

Your assignment should be a maximum of 14,400 characters.*
* excluding your code, tables, table notes, figure notes, and bibliography

All of the requirements below are standard in basically all working papers in political science and for submission to journals, so please stick to the following conventions:

  • 12-point font
  • 1 inch margins
  • Double-spaced
  • No Table of Content
  • 14,400 characters maximum
    • Excluding your code, tables, table notes, figure notes, bibliography

If you write your assignment in LaTeX (e.g. Overleaf) it’s therefore:

  • \documentclass[12pt, A4]{article}
  • \usepackage[margin = 1in]{geometry}
  • \doublespacing after your \begin{document}

If you want to use the Overleaf template that I use for my own academic manuscripts, you can find it here.

Expectations

The technical side of your assignment should, of course, be well-executed. But make sure to focus a lot of your energy on the structure and clarity of your writing. The reason that students often do not receive the grade that they might hope for is because the written part of their assignment is unclear. A few points:

  • When discussing a method or test used in the article, provide the intution behind it in plain language (non-technical, non-abstract langauge)
    • i.e. explain a method or test in plain non-technical language before turning to any abstract or technical language
  • When discussing a statistical test, provide the theoretical or substantive reason why it is being used (again, in plain, non-technical, non-abstract language)
  • Even if your audience understands the technical side of things, you always want to give a reader some intuition behind what you’re doing

Instructions

Data: Assignment_2B_Data.zip

Note: The author uses time (year) and city (panelvar) fixed effects in all of her models. She clusters her standard errors at the city level (panelvar). The numerical results in your assignment should almost exactly match the numerical results in the paper that you are replicating.

Codebook:

year: Year
panelvar: City
treated: Whether city i in year y is treated
treated_psm: Whether city i in year y is treated (for a propensity score matched sample)
newsd: Any rackeeting news
news_pc: Rackeeting news per capita
anyseiz: Any goods seized from the mafia
imm_seized: Goods seized from the mafia

Introduction

  1. Briefly introduce the article that you are replicating:
    - Introduce the topic
    - Introduce the research question
    - Introduce the hypothesis or hypotheses

Research design

  1. Explain the author’s research design:
    - The empirical strategy and data
    - The identifying assumptions
    • i.e. how does their research design allow them to estimate a causal effect and what are the potential threats to causal inference?
    • Note: It should be clear from this section that you know how a difference-in-differences research design works.
    • Note: The author suggests that the intervention needs to be as-if random. Note, however, that as-if randomness is not the identifying assumption of a difference-in-differences design. Her suggestion seems to be that it’s more likely that the parallel trends assumption will be violated if the treated and untreated units are very different from each other in a general way, which is a fair concern though.

Analysis

  1. Replicate Figure 2 from the article.
    - Use the News dataset to create the summary data that go into this figure.
    - Explain what the figure is showing and why the author is showing it.
    - It might look something like this, but make it look however you want:

Example figure

  1. Replicate the Two-Way Fixed Effects results from Figure 3, but do so as a table.
    - Models 1-4 use the News dataset; Model 5-8 use the Seized dataset.
    • treated and treated_psm implicitly define which dataset is being used: treated_psm is NA for any observation that isn’t part of the matched dataset. i.e. you don’t need to subset here, just used treated in the odd-numbered Models (1, 3, 5, 7) and treated_psm in the even-numbered models (2, 4, 6, 8).
    • Important: the author uses only data from 2016 or earlier, so be sure to only use data that are year <= 2016.
      • Explain the table’s purpose and interpret each of the results.
      • Your table might look something like this, but make it look however you want:

Example figure

  1. Create an event study figure using a Two-Way Fixed Effects model for each of the four outcomes from Figure 3 (use treated rather than treated_psm for each of them).
    - You can show four separate figures or combine them into 4 panels in a single figure.
    - Again, the author uses only data from 2016 or earlier, so be sure to only use data that are year <= 2016.
    - Explain the purpose of an event study graph.
    - Explain the results and what they say about the authors main findings (i.e. those from Figure 3).
    - Your figure might look something like this, but, again, make it look however you want:

Example figure

  1. For each of the four outcomes from Figure 3, create an event study figure using a model designed to correct for the issues with staggered difference-in-differences data (use treated rather than treated_psm for each of them).
    • You can show four separate figures or combine them into 4 panels in a single figure.
    • Again, the author uses only data from 2016 or earlier, so be sure to only use data that are year <= 2016.
    • Explain the results of this figure and explain the reason why using a staggered difference-in-differences model is important.
    • Calculate the average treatment effect on the treated (ATT), and state how the results differ from those of the Two-Way Fixed Effects estimates that you calculated for the table in Step 2.

Example figure

Discussion

  1. Explain the overall findings of the article. One paragraph should suffice.
  2. Discuss the benefits and drawbacks of the research design as it is applied in the article.

Submission instructions

  1. Formatting requirements!

    • 12-point font
    • 1 inch margins
    • Double-spaced
    • No Table of Contents
    • 14,400 characters maximum
      • Excluding your code, tables, table notes, figure notes, bibliography

  2. Your code should be commented so that it is clear to me that you know what each piece of code does. You don’t need to be excessive, but comment your code in a way that you think is reasonable.

  3. If you are in a group, only one of you needs to submit the assignment. Just ensure that all of your student IDs are on the title page.

  4. Submit your assignment and R code separately. Please send your assignment as a PDF and use an equivalent file name across the files:

    • Assignment_2B.pdf
    • Assignment_2B.R

  5. Submit through Absalon under “Assignment 2B”.