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.
Summary
Let’s face it, many of us feel daunted by statistics. But we also know that colleagues and clients ask whether our research has “statistically significant” results. Erin’s book Design for Impact helps you to test your hypotheses about improving design, and she guides you through deciding on your effect sizes to help you get those statistically significant results. Caroline’s book Surveys That Work talks about “significance in practice” and she’s not all that convinced about whether it’s worth aiming for statistical significance. Watch this lively session where Erin and Caroline compared and contrasted their ideas and approaches - helped by your questions and contributions.
Key Insights
-
•
Understanding null hypothesis testing requires mentally flipping between positive and negative assumptions, which many find cognitively challenging.
-
•
The intimidating language and academic culture around statistics deter many practitioners from embracing it.
-
•
Moving fast is not the same as making progress; deliberate, slower decision-making aided by statistics leads to better outcomes.
-
•
Engineers are more receptive to statistics when involved early and can see clear benefits, though they resist extra coding work needed for experiments.
-
•
Statistical significance does not always equate to practical or meaningful significance in real-world decisions.
-
•
Effect size is a critical but often overlooked statistic that helps determine if a detected change is worth acting on.
-
•
Good survey design prioritizes asking useful questions over simply increasing the number of respondents.
-
•
Combining qualitative and quantitative research methods into a holistic approach improves understanding and reduces bias.
-
•
AI tools can provide rough drafts of survey questions but cannot replace human feedback tailored to specific audiences.
-
•
Building intuition about statistics and user data requires practice and embracing imperfection as part of learning.
Notable Quotes
"You have to think of a hypothesis, then the opposite null hypothesis, and try to disprove the null. It's quite confusing and flip-floppy."
"We're using math to try to understand the universe and what's real, and that makes statistics inherently hard."
"Fast is not a virtue in itself; we should move slower and act with intention to go in the right direction."
"Engineers don’t like writing more code, so extra work for experimentation can meet resistance unless they see clear learning outcomes."
"Statistical significance is a mathematical concept about chance; what decision makers often want is significance in practice."
"You get better results from asking one person a useful question than asking 10,000 people a silly question."
"Effect size tells you how large a change is, and many statistics books don’t cover it well enough."
"In research, hypothesis is just a fancy word for a guess you pull out of your ass to start testing."
"AI might give a first draft, but I still prefer asking real humans to understand how they interpret survey questions."
"Start with the basics: means, minimums, maximums, and ranges. It quickly becomes less mysterious and more fun."
Or choose a question:
More Videos
"Telling your team’s story explains the culture of your team and how someone could fit into it."
Jennifer KanyamibwaCreating the Blueprint: Growing and Building Design Teams
November 8, 2018
"Having a repo isn’t the same as having a strategy for socializing and evangelizing the research."
Brigette Metzler Dana ChrisfieldResearch Repositories: A global project by the ResearchOps Community (Videoconference)
August 27, 2020
"I like to engage my stakeholders as co-creators and co-discoverers because that makes persuasion so much easier."
Carl TurnerYou Can Do This: Understand and Solve Organizational Problems to Jumpstart a Dead Project
March 28, 2023
"Sometimes you have to make something wrong on purpose to learn and improve it with others’ help."
John Mortimer Milan Guenther Lucy Ellis Patrick QuattlebaumPanel Discussion
December 3, 2024
"An engaged designer is a retained designer."
Dante GuintuHow to Crush the Talent Crunch
September 8, 2022
"We tend to confuse the experience of people with user experience, and I’m less interested in user experience than in the experience of people."
Richard BuchananCreativity and Principles in the Flourishing Enterprise
June 15, 2018
"Every speaker before me had these pristine backgrounds. I’m a slob and feeling really self-conscious about it."
Dan WillisTheme 3: Intro
January 8, 2024
"Failure cake helped us eat our feelings and provided comfort during hard moments."
Dan WardFailure Friday #1 with Dan Ward
February 7, 2025
"Researchers are positioned at the nexus of insight and action."
Chris GeisonTheme Two Intro
March 28, 2023