Getting un-stuck at research work

data-culture Nov 17, 2026

Phew, this past week I've been wrangling with a couple of thorny projects both on and off work, which has burnt enough brain cycles that all I had left in my brain is the sense of being stuck. Hence, here we are!

During the course of research work, it's inevitable that we will occasionally get stuck trying to make sense of the data. This is true regardless of what branch or flavor of science you work in, whether it's your graduate thesis project, quantitative logs analysis, or some hands on observational and diary study. You do all the things you're supposed, look up relevant theories, design a study to try to answer your research question, collect the data that is supposed to neatly tell you the answer to your question... and despite it all you find yourself staring at your data in the late evening wondering what the heck are you going doing. When we write result papers, everyone does their best to make the result and analysis sound like the result of obvious inevitable scientific progress happening. The reality is rarely that pretty.

There's no set cause for getting stuck. Your data and study could just truly be that terrible and the data you collected is useless regardless of how much you torture it. Your data may be perfect, but for any number of reasons you're just mentally unable to come up with the correct analysis to find the result. You may actually have perfect data for a research question, but it's not your research question. Oftentimes, it's a mix of everything.

So, what's a poor time-constrained researcher to do? When you've got a looming deadline and no leads?

Talk it out with someone or something

Research communities flourish for a reason. I've often been stuck for days on a problem, only to find new inspiration when venting to a coworker over how something isn't working out. Just going through the trouble of vocalizing my thoughts was often a big help. Responding to well-meaning questions or advice from my speaking partner would also uncover things that was worth exploring.

I don't even mean you need to talk to a colleague or peer that's in the same line of work. Talking things out with designers, product managers, engineers, even if I have to adjust the level of details I can share. Programmers often recommend rubber duck debugging as a way to help with their own work, which is essentially the same thing minus the social aspect.

I know that many people doing data work feel like this isn't an option for them because they are living in these little silos where they feel they don't have a "peer" to talk to about work stuff.

Walking around oddly works

There's a fun 2014 study by Marily Oppezzo and Daniel Schwartz, "Give your ideas some legs: the positive effect of walking on creative thinking" that found that walking around, even on a treadmill in a blank room, helps with generating novel ideas. I've definitely had a large number of newsletter posts come to me during brief walks with the kid to/from school. Having a boost in the ability to generate novel ideas is an asset for being stuck. As far I can tell, walking to grab snacks and drinks can count if you do enough of it?

Dump stuff out of your brain

Another very common occurrence for me is that I'm working on a problem big enough that I can't keep it all the threads straight in my brain. So the solution that winds up unblocking me is finding a way to dump all the details out.

Sometimes that involves a stack of small squares of note paper that I fill with observations and comments. Systematically writing everything down gives me space to stop and review and articulate ideas, so it's like rubber ducking. The process also provides visual artifacts that can be manipulated and rearranged to help notice unexpected patterns.

Other times, instead of writing down a bunch of notes, I'll start writing out a "this is the story I have so far" report. 90% of time, I don't think the report is any good even as I'm putting words down. Regardless, it's an attempt to tell a story with what I have, and sometimes forced motion is better than sitting still in endless self doubt.

I work on putting the story down in steps and automatically go into fact-check mode on what I write. The poking and prodding of the base reasoning has the side effect of forcing me to focus on a single particular argument or chain of reasoning to the exclusion of everything else. That focus may only last for a couple of sentences, but it's focus. It's not me running in mental circles trying to find "the right idea". I'm just either propping up or ripping apart an argument. It's not quite a Zen state, but we're getting there.

Partway through the process, I'll realize that the whole thing I wrote leads to a narrative dead end. The whole thing, every last word, likely has to be scrapped in favor of something else. Which is great! It crossed off an idea that was important enough that it didn't let go. Now it's gone and I can move on. The actual good idea may be another three dead drafts out, but closer nevertheless.

I get stuck a lot

Looking at all the productive, smart, folks that are all around me, they're always appearing like they're doing great work. Meanwhile I get into these stuck patterns on a regular basis. I'd bet once a week or more. I know that it's 100% just the Instagram effect of how I can't see the inner mental lives of all those folks. Odds are, the majority of them bang into issues and blocks at a similar rate. They just don't show it because it's just not a thing people tend to do.

But hey, I'm sure y'all get stuck in similar ways and work through it eventually, just like everyone else. It's good to believe none of us are alone in that.


Standing offer: If you created something and would like me to review or share it w/ the data community — just email me by replying to the newsletter emails.

Guest posts: If you’re interested in writing something, a data-related post to either show off work, share an experience, or want help coming up with a topic, please contact me. You don’t need any special credentials or credibility to do so.

"Data People Writing Stuff" webring: Welcomes anyone with a personal site/blog/newsletter/book/etc that is relevant to the data community.

Counting Stuff Official Forums: Discuss posts, or other data topics with the community.


About this newsletter

I’m Randy Au, Quantitative UX researcher, former data analyst, and general-purpose data and tech nerd. Counting Stuff is a weekly newsletter about the less-than-sexy aspects of data science, UX research and tech. With some excursions into other fun topics.

All photos/drawings used are taken/created by Randy unless otherwise credited.

Supporting the newsletter

All Tuesday posts to Counting Stuff are always free. The newsletter is self hosted. Support from subscribers is what makes everything possible. If you love the content, consider doing any of the following ways to support the newsletter:

  • Consider a paid subscription – the self-hosted server/email infra is 100% funded via subscriptions, get access to the subscriber's area in the top nav of the site too
  • Send a one time tip (feel free to change the amount)
  • Join the Approaching Significance Discord — where data folk hang out and can talk a bit about data, and a bit about everything else. Randy moderates the discord. We keep a chill vibe.
  • Get merch! If shirts and stickers are more your style — There’s a survivorship bias shirt!

Tags