Log in or create a free Rosenverse account to watch this video.
Log in Create free account100s of community videos are available to free members. Conference talks are generally available to Gold members.
Casual Inference
Summary
You've probably heard the old adage "correlation does not imply causation" but at some point we've got to say that drinking boiling hot tea and burning our tongues are more than just "strongly correlated". Enter Causal Inference, a collection of techniques for reasoning about the relationship between effects that can be measured and causes that can be identified. It helps us bridge between what we hear when we talk directly to users and what we observe about their behavior at scale and over time. This talk will introduce some of the key techniques in causal inference and how they can be used by UX Researchers and Designers to understand potential users, current users, and the products we might build.
Key Insights
-
•
Causal inference bridges qualitative reasoning about context with quantitative analysis of data.
-
•
Directed acyclic graphs help visualize causal pathways and common pitfalls like confounders and colliders.
-
•
Randomized controlled experiments require random assignment, blinding, and pre-specified hypotheses to measure causal effects reliably.
-
•
Average treatment effect summarizes impact on an entire population, whereas intent-to-treat reveals experiment adherence issues.
-
•
Quasi-experimental methods like regression discontinuity and difference-in-differences allow causal inference when randomization is not possible.
-
•
Matching is an art, relying on context-aware ranges rather than exact numeric equivalence to equate comparison groups.
-
•
Synthetic control methods build counterfactual scenarios when no good control group exists.
-
•
Understanding and designing for interpretability strengthens collaboration between designers and analytics or marketing teams.
-
•
Qualitative research poses valuable questions; quantitative causal inference sharpens and tests these questions.
-
•
Behavioral causes revealed by causal inference may differ from user self-reported reasons, offering deeper insights.
Notable Quotes
"Correlation doesn’t imply causation, but sometimes two things happening together do imply a causal mechanism."
"Qualitative reasoning about causal mechanisms usually comes from lived experience, either the researcher or participants."
"Designers have a hard time interpreting econometrics-driven quantitative research without bridging approaches."
"Random assignment to treatment or control is essential—if it’s not random, it’s not a true experiment."
"If you cannot remove a treatment, it may not be a true cause."
"Matching is very much an art, not a science; there are no hard and fast rules for what counts as a good match."
"Difference-in-differences lets you study treatment effects in groups that start in very different places by looking at trends."
"Synthetic controls create counterfactuals using historical data when no suitable control group exists."
"Qualitative research really poses questions; quantitative methods let you investigate those questions rigorously."
"You don’t want to overdesign just to make something more data interpretable because that can lead you down a dark path."
Or choose a question:
More Videos
"Embracing uncertainty means diving in without knowing the outcome and creating something new every time."
Jim KalbachJazz Improvisation as a Model for Team Collaboration
November 6, 2017
"Testing your book idea through workshops or talks gives a forcing function that helps prioritize content."
Louis RosenfeldCoffee with Lou: Should You Write a (UX) Book?
March 7, 2024
"Keeping your craft sharp, learning new tools like auto layout in Figma, and challenging yourself help maintain relevance."
Catt Small Micah Bennett Brian Carr Jessica HarlleeWhat's Next for ICs: Exploring Staff and Principal Designer Roles
February 22, 2024
"You might find that spending the most time getting people interested in collaboration is where the work really happens."
Marieke McCloskeyUser Science: Product Analytics & User Research
March 11, 2021
"Ultimately, AI avatar tools offer UX teams options to keep recordings while meeting legal compliance."
Llewyn Paine[Demo] Deploying AI doppelgangers to de-identify user research recordings
June 5, 2024
"Qualitative reasoning about causal mechanisms usually comes from lived experience, either the researcher or participants."
Joshua NobleCasual Inference
October 6, 2023
"We’re biologically wired to respond to intellectual challenges the same way as physical threats."
Sara LogelYour Colleagues are Your Users Too
March 29, 2023
"We are obligated to treat each other with kindness and respect; this is a safe and inclusive space."
Bria Alexander Louis RosenfeldWelcome
January 8, 2024
"Accessibility isn’t a checkbox you run automated tests for; you must involve people with disabilities to benchmark success."
Sam ProulxOnline Shopping: Designing an Accessible Experience
June 7, 2023