How to Think Like a Data Analyst | Step-by-Step Guide
1 Video View·Oct 17, 2024
In this video, Chris Dutton breaks down how to think like a data analyst using the Data Analysis Framework, an important topic for anyone looking to improve their data literacy skills.
We live in a world that runs on data. It's how Amazon and Netflix know which movies and products
to recommend, how Starbucks manages a global supply chain, and how Uber connects drivers
with passengers in real time. But the thing is, data skills aren't just for tech companies or
professional analysts anymore. Everyone works with data to some degree, and everyone can benefit from
data literacy skills. In this video, we're covering an important topic that will help you take your
data literacy to the next level. When it comes to transforming raw data into insight and ultimately
action, you need to think like an analyst. That means identifying the problem, setting clear
expectations, collecting and analyzing the exact information you need, and leveraging insights and
findings to influence decisions and real world outcomes. So here's a great analytical thinking
framework that we often teach here at Maven, which will help you take a more thoughtful and strategic
approach to your analysis. We cover this in much more depth in our Thinking Like an Analyst course,
but let's review it at a high level here as well, because it's extremely relevant to anyone trying
to make smart data-driven decisions, analyst or otherwise. Now keep in mind that there's still a
time and place for more unguided, open-ended exploratory analysis, but this approach works
very, very well, especially for explanatory analysis, where your primary goal is to deliver
actionable insights and recommendations. So it all starts by clearly identifying the problem you're
trying to solve, and the key here is that before you start thinking like an analyst, you need to
think like a business owner. And this involves asking yourself some key questions. What specific
problem are you trying to solve and which business outcomes are you trying to impact? Who are the key
stakeholders and how exactly will this help them? And does your approach align with the bigger
picture priorities and business strategy? Answering these questions first, which many people failed to
do, will help ensure that you align on the project scope and desired outcome from day one. The second
step in the framework is all about defining success, and this is where things like measurement
planning come into play. It's about asking yourself what exactly does a successful outcome look like
for the business? Is it driving more revenue, increasing employee retention rates, driving
better marketing ROI? And then once you've defined success, which specific metrics or KPIs will help
you quantify it, and what data will you need to capture to track those key metrics? That will set
you up with a crystal clear roadmap for measuring the success of your efforts. We see so many people,
even professional data analysts, skip these first two steps and jump straight into steps three and
four because they're so eager to roll up their sleeves and start playing with the data, which
often leads to disaster, wasted time for both you and stakeholders, lack of focus and clarity, false
hopes and expectations, and the list goes on. So if your goal is to work smart, not hard, and make a real
tangible impact, make sure you don't skip these steps. By the time you've reached step three, you
should have a clear picture of what success metrics you're trying to impact and the data you'll need
to quantify. Now is the time to start collecting and preparing your data. At this stage, the types
of questions you're asking are things like where is the data stored and how can you access it,
are there data quality issues that might skew the analysis, and is the data in the proper format,
or will it need to be transformed, modeled, or restructured to support your analysis?
This step can be one of the more challenging and time-consuming stages in the workflow
and typically involves a mix of QA, profiling, data cleaning, and enrichment, like adding new
fields or data sources, but if you do this well, it will create a rock-solid foundation for your
analysis and ensure that you're working with clean, high-quality data. Because as they say, garbage in,
garbage out. Step four is about finally getting your hands dirty and starting to explore and
analyze the data. For most people, this is the fun part because it involves slicing and dicing the
data, uncovering interesting patterns and trends, and ideally discovering some meaningful, actionable
insights that could directly impact the metrics you're trying to move. So the types of questions
you'll likely be asking at this point, which types of views of the data can help support your analysis,
which types of patterns and trends are beginning to emerge as you explore the data, and are you
finding any nuggets, any actionable insights that again could help drive those success outcomes.
Once you've wrapped the analysis phase, it's time to communicate your findings. This is another
mission-critical step, especially for explanatory analysis, because success hinges on your ability
to clearly communicate what you've found, why it's important, and how it can impact the business. One
of the most common missteps I see with young analysts is that they over-index on the technical
skills. They spend too much time getting fired up about the analysis itself, then completely drop
the ball when it comes time to share their findings, especially when they're communicating
with non-technical or senior-level audiences. At this stage, it's really important to remember that
people respond to stories, not data points. So you should be asking yourself how you can craft a
narrative to clearly summarize the key takeaways from your analysis. This is a great time to recap
your problem statement and measurement plan, summarize your approach, highlight your most
compelling insights, and tie it all together into a clear and concise presentation. You'll also be
thinking about the most effective ways to communicate your findings through data visualization,
which is something we'll talk more about in the next section, and confirming that your insights
are clear, compelling, and supported by the data. The final step in our framework is all about
advocating for action. When you stop short of this step, you're essentially taking the analysis to
the point where you're one step away from the finish line, and then leaving it up to your
audience to decide what to do from there. Don't make your stakeholders connect the dots on their
own. Think about what actionable, data-driven recommendations you can propose, and make sure
they directly tie to the success outcomes that you care most about. And the cherry on top, which will
make stakeholders absolutely love you, would be to propose how you might measure or quantify the
business impact of the changes you're proposing. Not only does that prove that you care about the
impact to the business, but it shows that you're willing to take accountability as well. Plus, if
all goes to plan, now you have an amazing success story to add to the resume. So that's a quick
summary of our data analysis framework, and even if you don't apply every single step, hopefully it
helps you at least get into a better analytical mindset that you can apply to your own work.
If you enjoyed this content and want to see more, we've got a brand new Data Literacy Foundations
course, and it's entirely free. You can check it out at mavenanalytics.io. So whether you're an
individual looking to build confidence, a leader seeking to empower and upskill your team, or a
data professional just trying to stay ahead of the curve, this is the course for you. We've got a lot
to cover, so let's dive in.

