Sociology 504: Social Statistics

Princeton University
Spring 2013
Lecture: Monday and Wednesday: 1:30pm - 3pm (Location: TBA)
Lab: Monday: 3:00pm - 4:30pm (Location: Stokes Library Computer Lab)
Instructor: Matthew Salganik
Preceptor: Jonathan Tannen

Source: XKCD

This course provides an introduction to social statistics.

There will be weekly problem sets given out each Wednesday and due the following Wednesday. Many of the problem sets will involve the statistical package R. You will be required to submit the code you used to complete your assignment and that code must comply with Google's R style guide. I know that the choice of R will lead to difficulties in the beginning of the semester, but there will be big payoffs later as you become more familiar with it. Regarding R, we will start slowly and assume that you do not have any programming experience.

You are encouraged to work together on the problem sets, but you must type all of your code yourself. That is, no copy-and-paste from other people's code. You would not copy-and-paste from someone else's paper, and you should treat code the same way.

In addition to problem sets, students will be expected to complete a final project. I will provide additional details about the final project in class. These final projects will be due Tuesday, May 14th (Dean's Day); no extensions will be given.

This class is required for all first year Ph.D. students in Sociology. If you are not a graduate student in sociology, please talk to me about whether this is the right course for you.

We will be using one book this semester:

We will also read chapters from the following books, but these will be available on Blackboard:

In this course we will be using Piazza for online class discussion. You will not be required to post, but the system is designed to get you help quickly and efficiently from classmates, the preceptors, and the professor. Rather than emailing questions to the teaching staff, I encourage you to post your questions on Piazza. Find our class page at:

A note on the use of open access scholarship: Because of the prohibitive cost of academic journals, many of assigned readings for this course are available only to people with access to a university library. I have marked these closed access articles with a . Fortunately, some of the more recent scholarship in this area is freely available to everyone in the world. I have marked these open access article with a . It is my hope that eventually I will be able to construct this syllabus using exclusively open access scholarship. In the meantime, copies of many of the closed access articles can be found through Google Scholar.

Below are the readings assignments for each week. You should come to class having looked at this material and you should read it roughly in the order listed. I will distinguish the Fox books by calling them Fox and Fox (R book).

Introduction (2/4/13)

What are we doing and what is regression? (2/6/13)

Week 1 Lab: Introduction to R (2/4/13)

The magic of seeing clearly (2/11/13)

Visualizing data and transforming data (2/13/13)

Week 2 Lab: Visualizing data (2/11/13)

Single variable regression (2/18/13)

Multiple regression (2/20/13)

Week 3 Lab: Regression and multiple regression (2/18/13)

Cause and effect in theory (2/25/13)

Cause and effect in practice (2/27/13)

Week 4 Lab: Causality

Dummy variable regression and interactions (3/4/13)

Dummy variable regression and interactions in practice (3/6/13)

Week 5 Lab

Statistical inference for regression (3/11/13)

Beyond star gazing (3/13/13)

Week 6 Lab

A matrix based approach to regression (part 1) (3/25/13)

A matrix based approach to regression (part 2) and introduction to maximum likelihood (3/27/13)

Week 7 Lab: Introduction to missing data

Regression diagnostics (4/1/13)

Diagnostics in action (4/3/13)

Week 8 Lab

Logit and probit models for categorical response variables (4/8/13)

Logit and probit models: They are not as simple as you thought (4/10/13)

Week 9 Lab

Models for polytomous data (4/15/13)

Introduction to generalized linear model (4/17/13)

Week 10 Lab

Introduction to multilevel modeling (4/22/13)

Case studies: Social networks and statistics (4/24/13)

Week 11 Lab

Case studies: Social policy experiments (4/29/13)

What we can and cannot do; what we should and should not do (5/1/13)

Week 12 Lab

Additional material

Creative Commons License
This course material is licensed under a Creative Commons Attribution 3.0 Unported License.