Quantitative UX research is a growing sub-field of UX research. Whether you’re a qualitative UX researcher looking to broaden your skills or someone from a related field looking to pivot, it can be hard to know how to build your quantitative UX research skills. This shares four pillars to learn quantitative UX research and some resources you can use to dive into any of those pillars.
Jump straight to the resources.
The four pillar of quantitative research
What are the pieces that make up the discipline of quantitative UX research? The most comprehensive book on the discipline right now is Quantitative User Experience Research (2024) by Chris Chapman and Kerry Rodden. The introduction section lays out three core skills for a quant UXR: UX research, statistics, and programming. I agree with these, but I prefer to focus on four pillars (rather than three) that provide tangible learning paths for people interested in quantitative UX research.
While the same book will show that the definition of a quant UXR role is nebulous, we do see some norms emerging. Maria Cipollone analyzed job postings in 2022 for the quant UXR title: she found strong consistency for the required skill of survey methodologies in quant UX research roles. While the survey domain of quant UXRs is not absolute, it’s widely applicable in a descriptive way.
This leads me to breaking the UX research skill in two pillars1. UX research is a broad area on its own, and to focus on that as a skill without some narrowing might leave newcomers lost. We already know surveys are important, so that is the first pillar. The second pillar to come out of UX research is research design, or how we build studies to reduce bias and increase validity of our claims2.
That gives us the four pillars for learning quantitative UX research skills: statistics, surveys, programming, and research design. This serves as a strong base for learning quant UX research, but it’s certainly not impeachable. Some quant UXRs will lean heavily into just one pillar. Other skills are also important, though I consider them more peripheral or ill-defined (stakeholder management, product thinking, etc.). That said, if you just want to dive into quant UX research, these pillars will not serve you wrong.
How to learn the pillars
There is no right or wrong way to learn to be a quantitative UX researcher. There is no degree that will singularly prepare you for this field. The tactics can vary but most quant UXRs have a blend of formal education, self-study, and on-the-job practice.
My path began formally. I completed a PhD in human factors psychology. Even at that point, I questioned if I could hold the title of quantitative UX researcher. I continued to self-study specific methods I didn’t know as well like survey weighting and MaxDiff, and on-the-job training was crucial for things like quant research operations and product impact.
I have a lot of thoughts about whether or not grad school is helpful for quant UX research, but that will need to wait for an upcoming post in my blog.
For this post, I’ll share some self-study resources for people that want to up-skill their UX research skills on the quant side, or fill in some gaps pivoting in from another field.
Why are you here?
If you find your reason in this list, I can provide some basic tips for quant UX research self-learning. If you can’t find yourself on the list, feel free to ask a question in a comment on the related LinkedIn post or contact me directly.
I need to run a survey and I only have a day to figure out how to do it in a quantitative way.
Read the last chapter of Surveys That Work for your general approach to developing a survey. Then, use this blog post from MeasuringU to create confidence intervals for your results. The first and most basic thing you can do to go from qual to quant analysis of surveys is by figuring out how sure you should be about your results.
I am a qualitative researcher already and I want to learn more about surveys.
You probably know a lot about research design and the basics of surveys (because in some ways a good survey question is similar to a good interview question, and perhaps you’ve written your fair share of screener surveys).
Read Surveying the User Experience to take your intuitive knowledge about asking good questions to empirically tested approaches for survey design and use the latter half of the book to learn about analyzing the data with statistics.
If you lack the tooling for analysis, try the swirl package to get some R basics down.
I am a student who wants to up-skill for the path of quantitative UX research.
You could certainly read some of the books I list below, but if you have time left, I’d highly suggest finding an elective course that focuses on survey design and/or statistical analysis (bonus if that stats course is taught with R/python). These may give you the chance to do a hands-on project you could use in a portfolio.
I am a mixed-methods UX researcher who wants to become a quantitative UX researcher or build that skillset to be more robust.
Are you sure you’re not already qualified? 🙂
You don’t need to know machine learning or Bayes to be a quant UX researcher. In some jobs, you may not even need to know how to program at the outset (some amazing quant UXRs I knew at Meta used SPSS for their analyses). I had the title of quant UX researcher before I felt fully qualified, even though I was, in retrospect.
Look at the pillars and choose the one you feel least confident in. Start with resources below that are tagged with that pillar. Go to the next Quant UX Con and see what kinds of problems quant UX researchers and mixed-methods researchers alike are working on.
I’d recommend Quantitative User Experience Research as the book to read to understand how skills you may already have are typically applied in a quant UX research role.
Self-study resources list
Many people find online courses helpful – I will not share them here because I took most of my courses during grad school, so I don’t have experience with online courses. Most of what I share here are books, but also a few blogs, websites, and papers that are especially useful. I’ll break it down by types of media and what pillars each book covers (they often touch more than one).
Notes about programming: R vs. Python
I focus primarily on R resources rather than python – it’s simply because I learned it first and know it best. My loosely held opinion is that R focuses on data cleaning, statistical analysis, and data visualization. It does those things more easily than python and that is what we do most of in quantitative UX research. Python can do far more than R and does better for some analysis domains like machine learning – we typically do less of these in quantitative UX research right now.
The books I’ve shared are excellent and many blend statistics heavily with R. Learning R is best done on the job in my opinion, so I don’t share any books that just focus on R. The programming pillar is the one where books fall the shortest – most coding is best learned “on-the-job”. This isn’t to say you need to be in a job, but programming needs to have a job – you should have a specific goal you want to accomplish, as soon as you learn the most basic syntax. You can’t really “learn R” because it’s made of an ever-expanding set of libraries/packages you load in as you need them.
I learned R at Red Hat because I wanted to graph adjusted-wald confidence intervals for binary data. Google Sheets (my only available statistical software) could not graph asymmetric confidence intervals which normally arise from adjusted-wald confidence intervals. Therefore, I learned R to graph those asymmetric confidence intervals in ggplot. I had a narrow focus, but it has obviously turned into a much bigger endeavor for me. Once I learned R, I found most things felt easier in R than Sheets/Excel.
A last note on programming – you need to learn R or python or data cleaning/analysis/visualization. However, most of the time you obtain large quantitative data via SQL, so that is useful to learn as well (and it’s pretty easy to get proficient). I wrote an article just for that.
Books
- Quantitative User Experience Research: Informing Product Decisions by Understanding Users at Scale
- Chris Chapman and Kerry Rodden, 2024
- Pillars: surveys 🔴, statistics 🟡, programming 🔵, research design 🟣
- This book won’t dive as deep into any pillar, but it pulls all of the core concepts together and talks in detail about the tendrils that connect them. There are tons of concrete, tactical examples (like the MaxDiff section), but it is primarily a view of the whole domain of quant UX research. If you don’t know how to calculate a confidence interval, I wouldn’t start with this book (though the first few chapters may be useful for general orientation to the field).
- Quantifying The User Experience: Practical Statistics For User Research
- Jeff Sauro and Jim Lewis, 2016
- Pillars: statistics 🟡, programming 🔵 (if you get the companion)
- If you aren’t sure what a confidence interval is or how to calculate it, start here. This is often my go-to recommendation for statistics. It’s the strongest blend of application with UX research and fundamental statistics theory. You can get R or Excel companions as well which make it easier to fold into your workflow. It has a bit of a human factors lens, compared to a market research lens, so that is probably my bias showing through.
- Surveys That Work: A Practical Guide for Designing and Running Better Surveys
- Caroline Jarrett, 2021
- Pillar: surveys 🔴
- This book is ideal for newcomers to surveys. It blends a bit of theory with lots of pragmatic instruction, cut with a few real anecdotes from industry. By the end you’ll know how to write effective survey questions, figure out the logistics (we call it research operations in industry terms) and analysis/presentation. There is also a bonus chapter to give you the basics in 5-10 minutes.
- Surveying the User Experience: Design and Analysis of Surveys for UX and Customer Research
- Jeff Sauro and Jim Lewis, 2024
- Pillars: surveys 🔴, statistics 🟡
- This book is much more academic than Surveys That Work. It will cover in detail things like sampling strategies, measurement error, and formal biases. It still covers the nuts and bolts of real survey work, like where to find participants and how much to pay them. A big strength of this book is the primary research the authors did to understand things like how many scale points to use or how top 2 box scores affect results. They also go to a moderate level of depth on statistical analysis methods for survey questions.
- Learning statistics with R: A tutorial for psychology students and other beginners
- Danielle Navarro, 2019 (not fully published)
- Pillars: research design 🟣, statistics 🟡, programming 🔵
- This book is nearly the full package: research design, R, and statistics. I found it for its research design chapter (which is an excellent primer), but it can be a great resource if you want a consistent set of materials to cover the most ground out of the quant UX learning pillars. It does not apply these concepts to UX research directly.
- Measuring the User Experience: Collecting, Analyzing, and Presenting Usability Metrics
- Tom Tullis and Bill Albert, 2013
- Pillars: surveys 🔴, statistics 🟡, research design 🟣
- This was one of the first quantitatively-focused UX research resources. Much of it is descriptive of certain UX research metrics, rather than going deep into statistics. For that reason, it’s a better resource if you want something lightweight. Perhaps due to the era of UX research when it was originally published, it does focus quite a bit on evaluations of usability.
- Discovering Statistics Using R and RStudio
- Andy Fields, 2012 (2025 edition available for pre-order)
- Pillars: statistics🟡, programming 🔵
- This book comes in versions for R, SPSS, SAS, and other statistical packages. It’s a common resource for psychology graduate students. It gets well into the theory and approaches it from a psychological experimental design lens – I find this lens quite valuable for UX research. It is less applied and is certainly a longer read than the ones above if you do all of the homework.
- Statistical Rethinking
- Richard McElreath, 2015
- Pillars: statistics🟡, programming 🔵
- Frequentist statistics dominate quant UX research, but that may not always be the case. I am on my journey to learn Bayesian statistics, and this book is where I’ve started. Candidly, I am not done reading it yet, but what I have read so far shows it to be an intuitive telling of a complicated subject. By chapter 4-5 ,you’ll have the basic tools to start running some bayesian models in R.
- R for Marketing Research and Analytics
- Chris Chapman and Elea McDonnel, 2015
- Pillars: surveys 🔴, statistics 🟡, programming 🔵, research design 🟣
- I consider quantitative UX research a blend of marketing research and human factors traditions. This book is a great way to learn more about the marketing research approaches for things like key driver analysis. The R sections are substantial enough to start from nothing and get to running analyses.
- Research Design: Qualitative, Quantitative and Mixed Methods Approaches
- John Creswell, 2023
- Pillar: research design 🟣
- This is an academic text, and covers qual and quant, but its section on quantitative design is really useful. It goes beyond surveys so you can start thinking about experimental and quasi-experimental designs which are useful for behavioral measures or assessing the quality of a/b experimentation. On top of that, it has a section on threats to validity – this is something I think all researchers should understand strongly. This material might be hard to see immediate impact on your UX research work, but is likely to make your findings closer to the “truth” that you’re seeking. I’d recommend this one if you want a deep dive on research design.
- The Visual Display of Quantitative Information
- Edward Tufte, 2001
- Pillars: statistics 🟡 (data visualization)
- While not strictly statistics, it’s such an essential tool in analysis I would be remiss to not mention a few data visualization resources. The book’s original version was published in 1983, but it’s still a good one. It won’t tell you how to plot a linear regression but it will give you the philosophical tools to make the right choices yourself.
- Good Charts: The HBR Guide to Making Smarter, More Persuasive Data Visualizations
- Scott Berinato, 2023
- Pillars: statistics 🟡 (data visualization)
- Newer than Tufte, this pulls in some more modern citations motivating the recommendations and is more applied for the business world.
Blogs, blog posts, and papers
- Quant UX Blog
- Chris Chapman (and guests)
- Pillars: surveys 🔴, statistics 🟡, programming 🔵, research design 🟣
- Chris has some great personal blog posts, but other pieces feel like a natural extension of his book that focus on the details of specific methods and how to execute great quant UX research in general. Chris has a marketing research focus in most content.
- MeasuringU
- Jeff Sauro, Jim Lewis (and guests)
- Pillars: surveys 🔴, statistics 🟡, research design 🟣
- The content is qual and quant, but it has a quant-leaning focus. It also is characterized by getting into the weeds with the exact calculations you need to do what the post is talking about. The authors have a usability and summative evaluation focus in most of the content.
- Counting Stuff
- Randy Au
- Pillars: statistics 🟡, programming 🔵, research design 🟣
- Randy’s work focuses more on the analytics/log side than surveys – this is a nice resource because that info is harder to find outside of a data science lens.
- Research Methods Knowledge base (or PDF form)
- Willam Trochim
- Pillar: research design 🟣
- This is a great primer on research design and how it is practiced. While academic, it’s condensed enough that I recommend it as the one resource to read if you don’t know anything about research design.
- Meta Research Medium Blog
- Various authors
- Pillars: surveys 🔴, research design 🟣
- Meta researchers share their best practices here. It’s qual and quant, but there are some extremely useful blog posts for survey best practices built from industry trials. It appears that the publication is no longer active, but lots of useful stuff remains.
- Figures and Frameworks
- Carl J. Pearson
- Pillars: surveys 🔴, statistics 🟡, programming 🔵, research design 🟣
- Hey, you’re already here! Did you know my blog has a title now? If you click the link, you’ll find all of my posts and a handy way to sign up to get it right in your inbox.
Websites and other resources
- Quant UX Conference
- Pillars: surveys 🔴, statistics 🟡, programming 🔵, research design 🟣
- The free conference proceedings available here are highly applied and valuable. It’s also a well-priced and friendly remote conference, so I’d suggest attending if you want to learn more about quant UX research.
- Swirl
- Pillar: programming 🔵
- This isn’t really a website, it’s a package for R where you can learn R in the R environment. A great way to get your hands dirty with basic syntax.
- Khan Academy: Statistics and probability
- Pillar: statistics 🟡
- I haven’t used this, but I know of people that have found it helpful to learn the basics of stats in a more interactive way.
- SQLBolt
- Pillar: programming 🔵
- Like other coding, SQL is best learned by doing right from the start. You can run test queries right in your browser.
- W3Schools
- Pillar: programming 🔵
- Similar to SQLBolt but it is more of a dictionary-style reference. It’s a handy reference for understanding basic syntax.
Wrapping up
Quant UX research is a growing discipline in UX research and a useful skill set for any UX researcher. At the beginning, I laid out four pillars for learning quant UX research, so you can focus on the area that needs the most attention: surveys, statistics, programming, and research design. The list of resources I shared is not exhaustive but highlights some tremendous books, websites, and other materials that will help you take your quantitative UX research skills to the next level. I may also continue to add resources I find most helpful, so watch for updates.
Appendix
- Chris Chapman also uses a similar breakdown in his article Notes on Quantitative UX Research at Google, including statistics, programming, UX research, and research design. UX research becomes a bit self-referential here, though I see the value of it. For example, I do a lot of usability benchmarking which better fits into the label of UX research than any of my proposed pillars. However, this is more of an edge-case method (like eye-tracking, for example). For someone looking for the most prototypical description of quant UX research to aid in their initial learning, Surveys seems to most concisely fit as its own pillar. All this to say, Chris Chapman is most accurate, but my version may be more pragmatically useful in directing a learner’s limited attention. ↩︎
- Longer definition: Research design is the overall strategy for answering a research question. Surveys and statistics are elements employed in research design. Research design covers both qualitative and quantitative methods. Obviously the focus here for a quantitative UX researcher should be on the latter, but it’s healthy to know the other side of the coin to avoid the problem of holding a hammer and only seeing nails. In other words, you need to know when surveys don’t apply so you don’t waste time or get invalid conclusions from your work. ↩︎