Probability
and Statistics

POLI_SCI 403

Fall 2025

Plan for today

  • Course topic

  • Who are we and why are we here?

  • Course overview

  • Lab 0

About this course

First in the PhD methods sequence:

  • POLI_SCI 403: (Introduction to) Probability and Statistics

  • POLS_SCI 405: Linear Models (Seawright)

  • POLI_SCI 406: Quantitative Causal Inference (Seawright)

Methods electives this year

Fall

  • Experiments (McGrath)
  • Small-N (Mahoney)

Winter: Machine Learning (Diaz)

Spring: Replication (Coppock)

Year-long: Statistical Computing Workshop (Diaz)

This course

Statistical inference: Using data we have to understand something for which we do not have data

Sample questions

  • What is the proportion of people who support criminalizing abortion?
  • What is the relationship between economic development and democracy?
  • Do voter ID laws affect turnout?

This course

Statistical inference: Using data we have to understand something for which we do not have data

Topics: Probability, estimation, inference, linear regression, maximum likelihood, causal inference

Theme: Make minimal assumptions

Who are we and why are we here?

Instructional team

Gustavo Diaz

Assistant Professor of Instruction in Political Science
Email:
Website: gustavodiaz.org
Office: Scott Hall 103

Artur Baranov

PhD Student in Political Science
Email:
Website: artur-baranov.github.io
Office: Scott Hall 110

You (again)

  • Name
  • Pronouns
  • Discipline + intended subfield/research area
  • Favorite food/artist/book/place

Course overview

Textbook

DO NOT BUY

DIGITAL COPY AVAILABLE THROUGH LIBRARY SUBSRIPTION

doi.org/10.1017/9781316831762

OR

NU Library URL

Additional readings linked in syllabus

Computing

  • R + RStudio for lab assignments and in-class demos

  • Local installation strongly recommended

  • Consider posit.cloud as backup

  • Other software allowed, no support guaranteed

Assigments

  1. Participation

  2. Lab assignments (9 total, due Mondays 11:59 PM)

  3. Replication paper (due December 10 9AM)

Contract grading

  1. Participation (satisfactory/unsatisfactory)

  2. Labs (satisfactory/unsatisfactory/fail)

  3. Paper (outstanding/satisfactory/unsatisfactory/fail)

Canvas rubric

0: Unsatisfactory
1: Satisfactory
2: Outstanding
NA: Fail

Baseline contract (B+)

  • Complete Lab 0
  • Be late on no more than one lab assignment
  • Submit final paper before deadline
  • Complete 7 out of 9 labs
  • Complete final paper
  • Satisfactory participation mark

Improving your grade

A-

  • Complete all labs

OR

  • Outstanding final paper

Improving your grade

A

  • Complete all labs

AND

  • Outstanding final paper

Weekly workload

  • ~3 hour lecture
  • ~1 hour TA section
  • One book chapter
  • 1-2 articles/videos
  • One lab assignment

Questions?

Lab 0

github.com/gustavo-diaz/ps403/blob/main/labs/lab0.qmd