How to Read Data Over Time

Most leaders I work with care deeply about their data. They review it regularly, discuss it with their teams, and try to make responsible decisions based on what they see.

But there is a common mistake that shows up again and again.

Leaders often read their data one point at a time.

A test score drops compared to the last assessment. Attendance rises compared to the previous month. Discipline referrals increase compared to the week before.

The natural move is to compare the newest number with the previous one and ask a simple question: Is this good or bad?

The problem is that this comparison usually tells us almost nothing about what is actually happening.

The Trouble with Two Points

Imagine looking at reading proficiency rates for a school.

Last year the rate was 61%.
This year the rate is 65%.

At first glance, it looks like an improvement.

But what if the eight years prior to the two most recent points looked like this?

63%
66%
60%
64%
62%
67%
59%
65%

Now the story looks very different. The most recent number may simply fall within the range the system has produced all along.

This is why one of the key lessons in data analysis is simple: Two or three data points are not a trend.

When leaders rely on point-to-point comparisons, they often assign meaning to movement that is perfectly normal.

Systems Produce Patterns, Not Points

Schools are systems. And systems produce results over time.

Attendance moves up and down. Assessment results fluctuate. Behavior incidents spike and dip.

This movement is not necessarily evidence that something improved or declined. Often it is simply the natural variation of the system.

When we examine only the most recent point, we lose the context needed to interpret what the data actually represents.

The question leaders need to answer is not: What happened this time?

The more important question is: How has this measure behaved over time?

Plot the Dots

One of the simplest and most powerful practices in improvement work is to plot the dots.

Instead of storing numbers in tables or reviewing them one at a time, we place each data point on a time-sequenced chart and connect them in order.

Once the data is displayed this way, patterns begin to appear.

Dr. Donald Berwick described the importance of this practice clearly:

“Plotting measurements over time turns out, in my view, to be one of the most powerful things we have for systemic learning.”

A simple run chart—data plotted across time—often reveals insights that a spreadsheet cannot.

We begin to see how much the data typically fluctuates. We see whether results are bouncing around an average or drifting in a particular direction. We see the behavior of the system, not just isolated outcomes.

Why This Matters for Leaders

Reading data over time changes how leaders respond when the numbers change.

Instead of reacting to the most recent result, leaders begin to ask better questions:

Is this point unusual compared to the pattern we’ve seen before?

How much variation does this system normally produce?

What should we expect if nothing in the system changes?

These questions slow the moment down. They help leaders distinguish between routine fluctuation and meaningful change.

And that distinction matters.

When leaders react to routine variation, they often introduce unnecessary pressure, shifting priorities, and new initiatives into systems that have not actually changed.

When leaders study patterns over time, they are far more likely to focus on the underlying system that produced the results.

Putting It All Together

When leaders read data one point at a time, they are forced to interpret every movement in the numbers.

But systems rarely behave that way. Systems produce patterns across time.

Three ideas can help leaders analyze their data more effectively:

Big Idea 1: Data should be viewed in context. A single data point has little meaning on its own.

Big Idea 2: Two or three data points are not a trend. Point-to-point comparisons often create misleading interpretations.

Big Idea 3: Plotting measurements over time reveals the behavior of the system and leads to better decisions.

In the next post, we will take the next step: learning how to determine when a change in the data actually represents a meaningful signal rather than routine fluctuation.

Whenever you’re ready, here are three ways to continue the work:

1. EMAIL JOHN
Have a question, an improvement idea, or a moment where the numbers changed and you weren’t sure how to respond? I regularly exchange ideas and resources with educators across the country and beyond, and I’d welcome hearing what you’re working through.

2. IMPROVEMENT ADVISING
If you’re looking for a thought partner who understands the realities of leading complex school systems, I work with leaders to strengthen decision-making, interpret data wisely, and build systems that improve over time—without adding noise or unnecessary initiatives.

3. WIN-WIN: THE BOOK
Win-Win is an improvement science text written for education leaders. It equips readers with the concepts and habits of mind from W. Edwards Deming’s System of Profound Knowledge to help them improve systems, not just react to results.

***

John A. Dues serves as the Chief Learning Officer for United Schools, a nonprofit charter management organization that supports four public charter school campuses in Columbus, Ohio. He is also the author of the award-winning book Win-Win: W. Edwards Deming, the System of Profound Knowledge, and the Science of Improving Schools. Send feedback to jdues@unitedschools.org.