A Crash Course in Causality: Inferring Causal Effects from Observational Data

Save on skills that make you shine with 40% off 3 months of Coursera Plus. Save now

A Crash Course in Causality: Inferring Causal Effects from Observational Data

Name: A Crash Course in Causality: Inferring Causal Effects from Observational Data
Rating: 4.699825479930192 (573 reviews)

Instructor: Jason A. Roy, Ph.D.

46,865 already enrolled

Included with

Learn more

5 modules

Gain insight into a topic and learn the fundamentals.

573 reviews

Intermediate level

Some related experience required

Flexible schedule

2 weeks at 10 hours a week

Learn at your own pace

90%

Most learners liked this course

5 modules

Gain insight into a topic and learn the fundamentals.

573 reviews

Intermediate level

Some related experience required

Flexible schedule

2 weeks at 10 hours a week

Learn at your own pace

90%

Most learners liked this course

Skills you'll gain

Tools you'll learn

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

16 assignments

Taught in English

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

There are 5 modules in this course

We have all heard the phrase “correlation does not equal causation.” What, then, does equal causation? This course aims to answer that question and more!

Over a period of 5 weeks, you will learn how causal effects are defined, what assumptions about your data and models are necessary, and how to implement and interpret some popular statistical methods. Learners will have the opportunity to apply these methods to example data in R (free statistical software environment). At the end of the course, learners should be able to: 1. Define causal effects using potential outcomes 2. Describe the difference between association and causation 3. Express assumptions with causal graphs 4. Implement several types of causal inference methods (e.g. matching, instrumental variables, inverse probability of treatment weighting) 5. Identify which causal assumptions are necessary for each type of statistical method So join us.... and discover for yourself why modern statistical methods for estimating causal effects are indispensable in so many fields of study!

This module focuses on defining causal effects using potential outcomes. A key distinction is made between setting/manipulating values and conditioning on variables. Key causal identifying assumptions are also introduced.

What's included

8 videos3 assignments

8 videosTotal 128 minutes

Welcome to "A Crash Course in Causality"1 minute
Confusion over causality20 minutes
Potential outcomes and counterfactuals14 minutes
Hypothetical interventions17 minutes
Causal effects19 minutes
Causal assumptions19 minutes
Stratification24 minutes
Incident user and active comparator designs15 minutes

3 assignmentsTotal 90 minutes

Practice Quiz30 minutes
Practice Quiz30 minutes
Causal effects30 minutes

This module introduces directed acyclic graphs. By understanding various rules about these graphs, learners can identify whether a set of variables is sufficient to control for confounding.

What's included

8 videos2 assignments

8 videosTotal 86 minutes

Confounding7 minutes
Causal graphs9 minutes
Relationship between DAGs and probability distributions15 minutes
Paths and associations7 minutes
Conditional independence (d-separation)13 minutes
Confounding revisited9 minutes
Backdoor path criterion16 minutes
Disjunctive cause criterion10 minutes

2 assignmentsTotal 60 minutes

Practice Quiz30 minutes
Identify from DAGs sufficient sets of confounders30 minutes

An overview of matching methods for estimating causal effects is presented, including matching directly on confounders and matching on the propensity score. The ideas are illustrated with data analysis examples in R.

What's included

12 videos5 assignments

12 videosTotal 171 minutes

Observational studies16 minutes
Overview of matching13 minutes
Matching directly on confounders13 minutes
Greedy (nearest-neighbor) matching17 minutes
Optimal matching11 minutes
Assessing balance11 minutes
Analyzing data after matching20 minutes
Sensitivity analysis10 minutes
Data example in R17 minutes
Propensity scores12 minutes
Propensity score matching15 minutes
Propensity score matching in R16 minutes

5 assignmentsTotal 150 minutes

Practice Quiz30 minutes
Practice Quiz30 minutes
Matching30 minutes
Propensity score matching30 minutes
Data analysis project - analyze data in R using propensity score matching30 minutes

Inverse probability of treatment weighting, as a method to estimate causal effects, is introduced. The ideas are illustrated with an IPTW data analysis in R.

What's included

9 videos3 assignments

9 videosTotal 119 minutes

Intuition for Inverse Probability of Treatment Weighting (IPTW)12 minutes
More intuition for IPTW estimation10 minutes
Marginal structural models12 minutes
IPTW estimation11 minutes
Assessing balance10 minutes
Distribution of weights9 minutes
Remedies for large weights13 minutes
Doubly robust estimators16 minutes
Data example in R27 minutes

3 assignmentsTotal 90 minutes

Practice Quiz30 minutes
IPTW30 minutes
Data analysis project - carry out an IPTW causal analysis30 minutes

This module focuses on causal effect estimation using instrumental variables in both randomized trials with non-compliance and in observational studies. The ideas are illustrated with an instrumental variables analysis in R.

What's included

9 videos3 assignments

9 videosTotal 125 minutes

Introduction to instrumental variables11 minutes
Randomized trials with noncompliance12 minutes
Compliance classes17 minutes
Assumptions13 minutes
Causal effect identification and estimation17 minutes
IVs in observational studies17 minutes
Two stage least squares16 minutes
Weak instruments5 minutes
IV analysis in R16 minutes

3 assignmentsTotal 90 minutes

Practice Quiz30 minutes
Practice Quiz30 minutes
Instrumental variables / Causal effects in randomized trials with non-compliance30 minutes

Instructor

Instructor ratings

(148 ratings)

Jason A. Roy, Ph.D.

University of Pennsylvania

1 Course46,865 learners

Offered by

University of Pennsylvania

Explore more from Probability and Statistics

Status: Free Trial
Coursera
Uncover Causal Impacts Fast
Course
Status: Preview
Columbia University
Causal Inference
Course
Status: Free Trial
University of Minnesota
Causal Inference Project Ideation
Course
Status: Preview
Columbia University
Causal Inference 2
Course

Why people choose Coursera for their career

Felipe M.

Learner since 2018

"To be able to take courses at my own pace and rhythm has been an amazing experience. I can learn whenever it fits my schedule and mood."

Jennifer J.

Learner since 2020

"I directly applied the concepts and skills I learned from my courses to an exciting new project at work."

Larry W.

Learner since 2021

"When I need courses on topics that my university doesn't offer, Coursera is one of the best places to go."

Chaitanya A.

"Learning isn't just about being better at your job: it's so much more than that. Coursera allows me to learn without limits."

Learner reviews

5 stars
76.96%
4 stars
19.19%
3 stars
1.91%
2 stars
0.69%
1 star
1.22%

Showing 3 of 573

Reviewed on Dec 14, 2021

It will be better to give reviews of related applications in specific AI areas (e.g, computer vision, NLP, etc.) at the end of each of the sections of the lesson.

Reviewed on Apr 4, 2021

My work involves working with observational data. This course taught me to think in more formal and organized way on topics and questions of causal inference.

Reviewed on Nov 13, 2024

This is a great course to me! This course really helps me have a better understanding of what constitutes causal effects. I really appreciate him for this course!

View more reviews

Frequently asked questions

To access the course materials, assignments and to earn a Certificate, you will need to purchase the Certificate experience when you enroll in a course. You can try a Free Trial instead, or apply for Financial Aid. The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.

When you purchase a Certificate you get access to all course materials, including graded assignments. Upon completing the course, your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.

Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.