How to Make a Scatter Plot in Excel: Step by Step

To make a scatter plot in Excel, put your two sets of numbers in side-by-side columns, with the X values on the left. Select both columns, then go to Insert > Insert Scatter (X, Y) or Bubble Chart and choose Scatter. Excel plots one dot for each row.
From there, add axis titles, adjust the axis range, and add a trendline to show the overall pattern. You can also display the trendline equation and the R-squared value, and use the CORREL function to measure how strong the relationship is.
This guide covers each step, from preparing the data to reading the results. It also walks through a full example, ad spend against weekly sales, and a faster way to build the chart from an export. Steps come from Microsoft's support pages, read on November 18, 2026.
What a scatter plot shows
A scatter plot shows how two numeric variables relate. Each dot is one observation. Its position across the chart is the X value, and its height is the Y value.
Microsoft explains where scatter charts fit: they "are commonly used for displaying and comparing numeric values, such as scientific, statistical, and engineering data." They "can plot two groups of numbers as one series of xy coordinates."
A scatter plot helps you answer questions like these:
- Do higher ad budgets go with higher sales?
- Do larger orders take longer to ship?
- Does temperature affect energy use?
- Are there unusual points that do not fit the pattern?
The shape of the dots tells the story. Dots rising from left to right suggest a positive relationship. Dots falling suggest a negative one. A shapeless cloud suggests little or no linear relationship.
Scatter plot or line chart?
Scatter plots and line charts can look alike, but they treat the horizontal axis differently. Microsoft's rule is clear: "use a line chart if your data has non-numeric x values." For numeric x values, Microsoft says a scatter chart is usually better.
In a line chart, the X values are categories spaced evenly, even if the numbers are uneven. In a scatter chart, the horizontal axis "is always a value axis," so each point sits at its true numeric position.
Use a scatter plot when both columns hold measured numbers, such as spend and sales. Use a line chart when the X values are labels or evenly spaced periods, such as months.
Prepare your data
A scatter plot in Excel needs two columns of numbers:
| Column A (X) | Column B (Y) |
|---|---|
| The variable you think drives the change | The variable you think responds |
Follow these rules:
- Put X on the left. Excel uses the first column for the horizontal axis.
- Use numbers only. Remove currency symbols typed as text, and units like "kg."
- One row per observation. Each row becomes one dot.
- No blank rows. Blanks can split the selection.
- Add clear headers. Short headers like "Ad spend ($k)" become easy axis titles.
If your data sits in a larger export, copy the two columns you need into a new sheet. That keeps the selection clean.
Insert a scatter plot in Excel
Microsoft's steps are short. Here they are for a basic scatter plot:
- Select the data you want to plot, including the headers.
- Select the Insert tab.
- Select Insert Scatter (X, Y) or Bubble Chart.
- Under Scatter, select the first option, which shows markers only.
Excel adds the chart to the sheet. Microsoft notes that you can "hover the mouse on any chart type to see its name" before you choose.
Avoid the scatter types with lines unless your X values follow an order, such as time. Lines between dots imply a sequence that most scatter data does not have.
If the chart comes out wrong, check which column Excel used for X. Right-click the chart, choose Select Data, and edit the series so the X and Y ranges are correct.
Add axis titles and set the axis range
A scatter plot without axis titles is hard to read. To add them:
- Select the chart.
- Select the Chart Elements button next to the chart.
- Check Axis Titles, then click each title and type a label.
Next, check the axis range. Excel often starts both axes at zero. If your values sit between 20 and 50, a zero start squeezes the dots into a corner.
To change the range, select an axis, then select Format Selection. Microsoft's guidance is to "type a different number in the Minimum box or the Maximum box." Select Reset to go back to the automatic value.
Microsoft notes a useful point about scatter charts. Because the horizontal axis is a value axis, "you can change the scaling options on this axis" just like the vertical one.
Marker style matters too. Select the dots, then select Format Selection. Make the markers a little larger and slightly transparent, so overlapping points stay visible. Keep one color unless you are comparing groups.
To compare groups, such as two regions, add each group as its own series. Right-click the chart, choose Select Data, and add a series with its own X and Y ranges. Each series gets its own color and its own trendline.
Add a trendline
A trendline shows the general direction of the dots. Microsoft's help says to "Add a trendline to your chart to show visual data trends."
To add one:
- Select the chart.
- Select the Chart Elements button at the top right.
- Check Trendline.
For more control, select More Trendline Options. Microsoft lists the types: Exponential, Linear, Logarithmic, Polynomial, Power, and Moving average.
For most business data, start with Linear. Try another type only if the dots clearly curve.
Check for outliers before you trust the line. One extreme point can pull a trendline far from the rest of the data. If a dot sits far from the others, find the row behind it. It may be a typing error, a one-off event, or a real result worth investigating.
Do not delete a real outlier just to get a cleaner line. Instead, note it on the chart, or show the trendline with and without it so readers can compare.
Trendlines can also project forward. In the Format Trendline pane, Microsoft says you can "Set a value in the Forward and Backward fields to project your data into the future." Use this with care, as the next sections explain.
Show the equation and R-squared
The trendline equation and the R-squared value turn the picture into numbers.
- Right-click the trendline and select Format Trendline.
- In the pane, check Display Equation on chart.
- Check Display R-squared value on chart.
The equation has the form y = mx + b. The slope, m, tells you how much Y changes for each one-unit change in X. The intercept, b, is the value of Y when X is zero.
R-squared runs from 0 to 1. It shows how much of the variation in Y the straight line explains. A value near 1 means the dots sit close to the line. A value near 0 means the line explains little.
Microsoft's trend guide notes that this is a form of regression analysis, "which estimates the relationship between variables." For a full regression with p-values, use the Analysis ToolPak.
Measure the relationship with CORREL
The chart shows the pattern. The CORREL function gives you a single number for its strength.
Microsoft says "The CORREL function returns the correlation coefficient of two cell ranges." The syntax is:
CORREL(array1, array2)
If your X values are in A2:A11 and Y values in B2:B11, enter:
=CORREL(A2:A11,B2:B11)
The result runs from −1 to 1:
| Value | What it suggests |
|---|---|
| Close to 1 | Strong positive relationship |
| Close to 0 | Little or no linear relationship |
| Close to −1 | Strong negative relationship |
For a simple straight-line fit, the square of CORREL equals the R-squared value on the chart. That is a quick way to check your trendline.
A worked example: ad spend vs. sales
Here is a full example. A small online store tracks weekly ad spend and sales for ten weeks, both in thousands of dollars.
| Week | Ad spend ($k) | Sales ($k) |
|---|---|---|
| 1 | 2.0 | 26 |
| 2 | 3.5 | 29 |
| 3 | 1.5 | 21 |
| 4 | 4.0 | 38 |
| 5 | 5.0 | 39 |
| 6 | 3.0 | 31 |
| 7 | 6.0 | 44 |
| 8 | 4.5 | 34 |
| 9 | 2.5 | 24 |
| 10 | 5.5 | 47 |
Select the Ad spend and Sales columns, not the Week column. Insert a scatter plot with markers only. Set the horizontal axis from 1 to 7 and the vertical axis from 15 to 50.
Add a linear trendline and display the equation and R-squared. Excel shows a line close to y = 5.418x + 12.98, with R-squared of about 0.90.
Then enter =CORREL(B2:B11,C2:C11). The result is about 0.95, a strong positive relationship. Squaring 0.949 gives about 0.90, which matches the R-squared on the chart.
Here is how to read it. Each extra $1,000 in weekly ad spend goes with about $5,400 more in sales, on average. The line explains about 90% of the week-to-week variation in sales.
Two cautions apply. First, this shows a relationship, not proof that ads caused the sales. A holiday or a price cut could drive both. Second, the data covers spend from $1,500 to $6,000. The line suggests about $50,900 in sales at $7,000, but that is outside the observed range, so treat it as a rough guess.
It also helps to look at the residuals, the gaps between each dot and the line. In this data, weeks 4 and 10 sit above the line, and weeks 2 and 8 sit below it. Ask what happened in those weeks. A promotion or a stock shortage often explains a large gap, and that context is worth a note on the slide.
A good chart title states the finding: "Weekly sales rise with ad spend (r = 0.95)."
Make a scatter plot in Excel with AI
Making the chart is quick once the data is clean. The slow part is often the data: pulling two columns from a large export, fixing text numbers, and finding outliers.
An AI tool can do that preparation and the analysis for you. Here is the method in three steps, using Powerdrill Bloom.
Step 1: Upload your Excel, CSV, or PDF file
Upload the file that holds your data, such as a marketing export or a sales report. The Scatter Graph Creator says it accepts "various formats like CSV and Excel."
Keep the columns you want to compare in the file. You can name them in the next step.
Step 2: Ask for the scatter plot in natural language
Describe the chart you need. For example: "Plot weekly sales against ad spend, add a linear trendline, and show the correlation." Ask it to point out any outliers.
The page says the tool "reveals hidden relationships through clean and accurate visualizations." Ask follow-up questions, such as whether the pattern differs by channel.
Step 3: Download the chart for your report or slides
The page says you can "Download your scatter graph as PNG in high resolution." Use it in a report or deck, or ask for a short written summary of the finding.
Check the correlation and the trendline against your own data before you share the chart.
Common mistakes to avoid
These are the problems that come up most often with a scatter plot in Excel.
- X and Y swapped. Put the driver on the left so it lands on the horizontal axis.
- Numbers stored as text. Text values do not plot. Convert them to numbers first.
- Using a line chart. A line chart spaces X values evenly and hides the real pattern.
- Axes starting at zero. Tighten the range so the dots fill the chart.
- Reading cause into correlation. A strong pattern does not prove one thing causes the other.
- Forecasting far outside the data. Trendlines are least reliable beyond your observed range.
- Too few points. Five or six dots can show a pattern by chance. Collect more rows before you draw firm conclusions.
For trends over time, see our guide on how to make a line graph. For spread and outliers within one variable, see how to make a box plot in Excel.
When your numbers sit in a large export, try Powerdrill Bloom to turn them into a ready scatter chart.
Frequently asked questions
How do I make a scatter plot in Excel with two sets of data?
Put the X values in the left column and the Y values in the right column. Select both, then choose Insert > Insert Scatter (X, Y) or Bubble Chart > Scatter.
How do I add a line of best fit in Excel?
Select the chart, select the Chart Elements button, and check Trendline. Choose Linear in the trendline options, and check the boxes to display the equation and R-squared.
What is the difference between a scatter plot and a line chart in Excel?
A scatter plot places each point at its true numeric X value. A line chart spaces X values evenly as categories. Use a scatter plot when both variables are numbers.
How do I find the correlation in a scatter plot?
Use the CORREL function on the two columns, such as =CORREL(A2:A11,B2:B11). A value near 1 or −1 shows a strong relationship.
Why is my scatter plot showing the wrong axis?
Excel may have used the wrong column for X. Right-click the chart, choose Select Data, and edit the series so the X and Y ranges are correct.
Sources: Microsoft Support, Present your data in a scatter chart or a line chart · Microsoft Support, Add a trend or moving average line to a chart · Microsoft Support, Predict data trends · Microsoft Support, CORREL function · Microsoft Support, Change the scale of the vertical (value) axis in a chart.