A few weeks ago, I was thinking about two completely different data analysis process experiences that happened years apart.
One involved a graduate student who was struggling with a data analysis assignment. The other involved a recent client engagement that required digging deeply into a dataset to understand what was really happening.
On the surface, the situations had very little in common. But the more I thought about them, the more I realized they shared the same underlying challenge. In both cases, the obstacle wasn’t a lack of technical skill or analytical ability. It was a discomfort with uncertainty.
As I was thinking about that, four words popped into my head:
Fortune favors the curious.
The phrase seemed to capture exactly what I’d been trying to put into words. The more I reflected on it, the more convinced I became that curiosity is one of the most important, and perhaps most overlooked, skills in analytics.
In this article, I’m using the term analytics broadly to include data analysis process, reporting, testing, optimization, and the process of using data to make better business decisions.
People often assume that experienced analysts have an almost magical ability to look at a dataset and immediately know where the insights are hiding. That’s certainly what I thought early in my career. I imagined that expertise meant recognizing patterns instantly or knowing exactly which report to run, which chart to create, or which metric would explain what was happening.
Experience certainly helps. But I’ve come to believe that’s not what separates great analysts from merely competent ones.
The best analysts aren’t the people who always know the answer. They’re the people who are comfortable not knowing.
That may sound like a contradiction. After all, aren’t analysts hired to provide answers?
Yes, but the best answers rarely appear the moment you open a spreadsheet. They emerge through a process of asking questions, exploring possibilities, testing assumptions, and following the evidence wherever it leads. Sometimes that data analysis process confirms what you expected. Sometimes it completely changes your perspective. Either way, you’ve learned something you didn’t know before.
Unfortunately, that’s also where many people become uncomfortable. They want to know, before they begin, that the next hour of analysis will produce a useful answer. They want assurance that the report they’re about to build or the chart they’re about to create will reveal the insight they’re looking for. If there’s a chance it won’t, they’re understandably reluctant to spend the time.
I understand that instinct. None of us likes wasting time.
The problem is that discovery doesn’t come with guarantees.
Reporting is Planned. Discovery Isn’t.
The conversation with my student came back to me recently while I was working on a client engagement.
We needed to analyze a large amount of customer data to understand what was happening and, more importantly, why it was happening. Early in the project, I was asked a perfectly reasonable question:
“What charts do you need?”
My answer surprised people.
“I don’t know yet.”
That wasn’t because I hadn’t prepared or because I didn’t have a plan. Quite the opposite. I knew the business questions we were trying to answer. What I didn’t know was what the data would reveal, and until I saw it, I couldn’t know which questions we’d need to ask next.
That’s the part of the data analysis process that I think is often misunderstood.
If the goal is routine reporting, you absolutely can begin with a checklist. Every month you calculate the same metrics, produce the same dashboards, and monitor the same trends. That’s valuable work because it tells you what’s happening over time.
Analysis is different.
Analysis begins with a question, but it rarely ends with the answer to that question alone. More often, the first answer leads to another question, which leads to another analysis, which uncovers something you weren’t expecting to find.
Imagine you’re looking at email performance and notice that click rates declined significantly over the past quarter. The first report tells you what happened. But it doesn’t tell you why.
So you begin asking questions.
Did the decline occur across every campaign, or only certain types of messages?
Was it consistent across audience segments?
Did it begin after a change in creative, cadence, or targeting?
Did it affect mobile users differently than desktop users?
Each answer suggests another question. Sometimes the trail ends quickly. Other times it uncovers something far more important than the question you started with.
That’s why I couldn’t answer the question, “What charts do you need?” before looking at the data.
The first set of charts would determine the second set of charts.
The second set of charts might determine that we need a third.
If you’ve ever worked through a particularly interesting dataset, you’ve probably experienced this yourself. You notice something that wasn’t part of your original hypothesis. It catches your attention. You investigate further. Suddenly you’re exploring an entirely different aspect of the data because it appears more interesting, or more important, than the question you originally set out to answer.
Those moments aren’t distractions.
They’re often where the most valuable insights are hiding.
Discovery Isn’t Linear
I think one of the reasons people struggle with this data analysis process is that we’re accustomed to work that’s linear.
We define the task.
We create the plan.
We execute the plan.
We deliver the result.
There’s comfort in that sequence because each step is known before we begin.
Discovery doesn’t work that way.
Discovery is iterative.
Every answer changes the next question.
Sometimes a data analysis process confirms your original hypothesis. Sometimes it disproves it. Sometimes it reveals that you’ve been asking the wrong question altogether.
That’s not a sign that the earlier work was wasted.
It’s evidence that the process is working.
I’ve found that many of the most valuable insights I’ve uncovered over the years weren’t answers to the questions I started with. They were answers to questions I didn’t even know to ask until I began exploring the data.
That’s one of the reasons I think curiosity is such an important professional skill.
Curious analysts don’t become discouraged when the first chart doesn’t reveal the answer. They simply ask, “That’s interesting…what does it mean?”
Then they keep going.
What Curiosity Looks Like During the Data Analysis Process
At this point, it’s probably worth clarifying what I mean by curiosity.
I’m not talking about aimlessly clicking through reports or randomly slicing a dataset in the hope that something interesting appears. That’s not analysis; it’s wandering.
Curiosity is much more disciplined than that.
Curious analysts begin with a question. They explore the data to answer it. Then they pay attention to what they find, especially when the answer isn’t what they expected. Rather than forcing the data to support their original hypothesis, they allow the evidence to shape the next question.
In other words, curiosity isn’t the absence of a plan. It’s the willingness to revise the plan as you learn.
Over the years, I’ve noticed that many of my data analysis processes follow a similar pattern. I begin with one business question, but by the time I’ve finished, I’m answering a different, and usually more important, question than the one I started with.
That isn’t because I lost focus.
It’s because the data showed me something worth pursuing.
Sometimes it’s an unexpected spike or drop in performance. Sometimes it’s a customer segment behaving differently than every other segment. Sometimes it’s a campaign that succeeded despite violating what I thought I knew about best practices. Those moments make me stop and ask another question.
Why did that happen?
Very often, that’s where the real data analysis process begins.
I’ve found that some of the most useful questions aren’t especially complicated. They’re simply questions that invite exploration rather than closure.
- Is this true across the entire audience, or only for certain segments?
- Has this always been happening, or is it something new?
- What changed between this campaign and the last one?
- Is this difference meaningful, or is it simply normal variation?
- What happens if I look at this from a completely different perspective?
One question I’ve learned to ask over and over again is simply, “That’s interesting…why?”
It sounds almost too simple to matter, but I’ve found it’s one of the most productive questions in analytics. It shifts your focus from reporting what happened to understanding why it happened. And once you understand the “why,” you’re much more likely to discover something worth acting on.
Notice that none of those questions assumes an answer.
That’s intentional.
The goal isn’t to prove that you’re right. The goal is to understand what’s actually happening.
That distinction is easy to overlook, but it’s one of the characteristics that separates reporting from analysis.
Confidence Isn’t the Same as Certainty
I also think we sometimes confuse confidence with certainty.
Confident analysts aren’t the people who believe they already know the answer. They’re the people who trust their ability to find the answer.
That’s an important difference.
When someone asks me a question about a dataset, I’m perfectly comfortable saying, “I don’t know yet.”
Not because I’m uncertain about my abilities.
Because I haven’t done the analysis yet.
There’s no reason I should already know the answer.
Ironically, I’ve found that experienced analysts are often more comfortable saying “I don’t know” than beginners. They understand that uncertainty isn’t evidence of incompetence. It’s simply the starting point of every meaningful investigation.
The confidence comes from trusting the process.
If I ask thoughtful questions, examine the evidence carefully, and remain open to changing my mind, I’m confident I’ll arrive at a useful answer.
It may not be the answer I expected.
It may not even be the answer to the question I started with.
But it will almost certainly teach me something valuable.
That’s what curiosity makes possible.
Curiosity Is a Professional Skill
We often think of curiosity as a personality trait. Some people are naturally curious, while others aren’t.
I don’t think that’s true.
Like critical thinking, curiosity can be practiced.
It begins by becoming comfortable asking one more question.
When you think you’ve found the answer, ask yourself whether there’s another explanation.
When something surprises you, resist the temptation to dismiss it as an anomaly. Investigate it.
When the data doesn’t support your hypothesis, don’t immediately conclude the analysis failed. Consider the possibility that you’ve learned something even more valuable.
Those habits don’t just make you a better analyst.
They make you a better problem solver.
The Lessons
- Great analysts begin with questions, not answers. They understand that meaningful insights emerge through exploration, not certainty.
- Reporting and analysis are not the same thing. Reporting answers the questions you already know to ask. Analysis uncovers the questions you didn’t know you should be asking.
- Curiosity is a disciplined skill. It’s not randomly exploring data; it’s asking thoughtful questions, following the evidence, and remaining open to changing your mind.
- Confidence isn’t certainty. Confident analysts don’t expect to know the answer before they begin—they trust the analytical process to help them find it.
- Discovery is iterative. Every answer leads to another question. That’s not inefficiency; it’s how learning and insight happen.
Fortune Really Does Favor the Curious
When I first thought of the phrase Fortune favors the curious, I liked it because it seemed to capture something I’d observed over the years.
Now, after reflecting on the two experiences that inspired this article, I think it captures something even more important.
The best analysts aren’t fearless.
They don’t begin every project knowing exactly what they’ll find. They don’t have a secret formula that tells them which chart to create or which query to run. They experience the same uncertainty the rest of us do.
The difference is that they don’t let uncertainty stop them.
Instead, they become curious.
They ask another question.
They look at the data from another angle.
They follow an unexpected result instead of dismissing it.
They allow themselves to change their minds when the evidence points in a different direction.
Over time, I’ve come to believe that’s one of the most valuable skills any analyst can develop. Not because curiosity guarantees success (it doesn’t), but because curiosity keeps you moving forward when certainty isn’t available.
And certainty is almost never available at the beginning of an analysis.
If you already knew the answer, there would be no reason to analyze the data in the first place (if only it were that easy).
Instead, analysis asks something different of us. It asks us to trust the process. To accept that every question won’t lead to a breakthrough, every chart won’t reveal a hidden insight, and every hypothesis won’t prove correct.
That’s not wasted effort.
It’s how discovery works.
Every possibility you eliminate brings you closer to understanding what’s really happening. Every unexpected finding teaches you something you didn’t know before. Every thoughtful question makes the next question a little better.
Eventually, what began as uncertainty becomes understanding.
Looking back, the path often seems obvious.
It never is while you’re walking it.
That’s why I think curiosity deserves more attention as a professional skill. We spend a great deal of time teaching analysts how to build dashboards, write SQL, create visualizations, and calculate metrics. Those are all important skills.
But the tools don’t tell us what questions to ask.
Only curiosity does.
So the next time you find yourself staring at a spreadsheet, a dashboard, or a report and wishing you knew exactly where to begin, remember that you don’t have to know the answer before you start.
You simply have to be curious enough to ask the next question.
Reporting answers the questions you already know to ask.
Analysis uncovers the questions you didn’t know you should be asking.
And in my experience, that’s where the most valuable insights are almost always found.
Fortune really does favor the curious.
Frequently Asked Questions
What’s the difference between reporting and analysis?
Reporting summarizes what happened. Analysis explores why it happened and uncovers questions you may not have known to ask.
Why is curiosity important in data analysis?
Curiosity helps analysts move beyond routine reporting to uncover patterns, relationships, and insights that lead to better business decisions.
Can curiosity be learned?
Yes. Curiosity is a professional skill that develops through practice. It begins with asking thoughtful questions and remaining open to unexpected findings.
Why is uncertainty part of analysis?
Because meaningful analysis is exploratory. If you already knew the answer before you started, there would be little reason to analyze the data.
What do you think?
Have you experienced a moment where curiosity led you to an unexpected insight? Or found yourself wanting certainty before starting an analysis? I’d love to hear your experiences in the comments.
Until next time,
jj
Jeanne Jennings is the Founder and Chief Strategist at Email Optimization Shop, a boutique consultancy and training organization where she helps clients craft more effective and more profitable email programs.
Learn more at www.EmailOpShop.com and sign up for our free newsletter to get more content like this.
Author’s Note
I believe in being transparent about my use of AI.
For this article, I used ChatGPT (GPT-5.5) as a thinking partner. It helped me organize ideas, explore different ways to present them, and improve the writing. The stories, insights, opinions, and final editorial decisions are all mine.
In many ways, this article reflects exactly how I believe AI should be used: not to replace expertise, but to amplify it.
