I'm sitting for the DAC in about nine weeks and trying to figure out where to put the most effort. I've been doing data analytics work for about four years — mostly SQL, some Python, a fair amount of Tableau — but I know exams don't always test the same things you actually use day-to-day.
I've been doing around two hours of studying most evenings, which I can sustain but don't have much room to push beyond. So far I feel okay about the technical analysis sections but I'm less confident in the data governance and ethics content. That stuff isn't something I deal with much in my current role and I don't have a great intuition for how it'll be framed on the exam.
If you've taken this exam recently, I'd love to know which areas surprised you the most. Also curious whether the statistics concepts go very deep — I'm comfortable with regression and descriptive stats but I haven't touched Bayesian methods in a long time and I'm not sure if I need to go back there.
I scored a 74% and the area that dragged me down was visualization best practices. It seems basic, but the exam gets into specific principles around accessibility, cognitive load, and chart selection in ways that go beyond what most of us practice intuitively.
The governance and ethics questions were more nuanced than I expected. They weren't straightforward right-or-wrong scenarios — a lot of them involved situational judgment. I'd give that section a solid two weeks of focused reading.
Coming from a four-year SQL and Python background you're probably in good shape on the technical side. The data quality and pipeline lifecycle questions caught me off guard — less about writing code and more about process knowledge.
Stats didn't go super deep for me, but knowing your probability distributions and being able to interpret p-values confidently is necessary. I didn't see anything requiring Bayesian computation, but conceptual understanding came up a few times.
Honestly I almost bailed around week five because the statistics and modeling concepts felt way more abstract than anything I'd touched in real work. SQL and dashboards? No problem. But the moment it got into probability distributions and model evaluation metrics I felt completely lost. What got me through was just accepting that some of this stuff you have to learn fresh regardless of experience level.
If I had to do it over I'd front-load the analytics and statistics domains hard, especially if your day-to-day is heavier on the BI and querying side like mine was. The data management piece wasn't as bad as I expected but don't sleep on it either. You've got nine weeks which is plenty of time if you're consistent, just don't let a rough practice test in week three make you think you're not ready.
Failed it the first time and honestly it wasn't what I expected. I had the same background as you — SQL daily, decent Python, Tableau certified — and I thought the analytics stuff would carry me. It didn't. The ML and predictive modeling questions wrecked me because I understood the concepts but couldn't work through the application questions fast enough. Second time I went deep on that domain specifically, did a ton of practice on it, found a good set of free dac machine learning predictive analytics questions that actually matched the style of what they ask, and passed with room to spare.
If you've got four years of real analytics experience the data governance and visualization domains will probably feel okay. Don't sleep on the statistical methods section either — it's more applied than you'd think and it'll catch you if you've been doing everything in a tool that handles the math for you. Nine weeks is plenty of time if you're honest about where you're weak.