How to Make a Scatter Plot in Tableau

Creating a scatter plot is one of the best ways to see the relationship between two different numerical variables in your data. This simple chart helps you instantly spot correlations, find outliers, and identify patterns that might be hiding in a spreadsheet. This guide will walk you through exactly how to build and enhance a scatter plot in Tableau, step by step.

What is a Scatter Plot and Why Should You Use One?

In simple terms, a scatter plot (or scatter diagram) uses dots to represent values for two different numeric variables. The position of each dot on the horizontal (X-axis) and vertical (Y-axis) axes indicates the values for an individual data point.

Think of it like this: you want to see if there's a connection between how much you spend on marketing campaigns and the sales revenue you generate. A scatter plot can visualize this relationship for you. Each dot on the chart could represent a single marketing campaign, positioned based on its cost (on the X-axis) and its resulting revenue (on the Y-axis).

Here’s why scatter plots are so useful for data analysis:

• Identifying Relationships (Correlation): Are the two variables related? You can quickly see if there's a positive correlation (as one variable increases, the other tends to increase), a negative correlation (as one increases, the other decreases), or no clear correlation at all.
• Spotting Outliers: Outliers are data points that fall far from the general pattern of the other points. A dot floating far away from the main cluster is easy to spot on a scatter plot and might warrant a closer look.
• Detecting Patterns and Clusters: You might notice that the dots form distinct groups or clusters. This could indicate different segments within your data, such as high-performing and low-performing customer groups.

They are perfect for answering questions like:

• "Is there a relationship between a customer's age and their average purchase value?"
• "Do higher website visitor numbers lead to more newsletter sign-ups?"
• "How does product discount percentage affect the total quantity sold?"

Creating a Scatter Plot in Tableau: Step-by-Step

Let's build a scatter plot from scratch. For this example, we'll use the "Sample - Superstore" dataset that comes included with every copy of Tableau Desktop. We'll explore the relationship between 'Sales' and 'Profit' for each customer.

Step 1: Connect to Your Data

First, open Tableau and connect to your data source. In the "Connect" pane on the left, under "Saved Data Sources," select Sample - Superstore. Tableau will load the data, and you’ll see the main workspace. On the left side, you'll find your data fields organized into Dimensions (categorical data like 'Customer Name' or 'Region') and Measures (numerical data like 'Sales' or 'Profit').

Step 2: Place Your Measures on the Shelves

Measures are the numbers you want to plot against each other. In our case, that's Sales and Profit.

• Drag the Sales measure from the Data pane and drop it onto the Columns shelf at the top of the workspace.
• Drag the Profit measure and drop it onto the Rows shelf.

Right now, your chart will show just a single point. This is because Tableau, by default, aggregates all your measures. That single dot represents the total sum of sales and the total sum of profit for the entire dataset.

Step 3: Break Down the Data to Create the "Scatter"

To turn this single point into a scatter plot, we need to tell Tableau how to break down the data. We want to see a single dot not for the whole company, but for each individual customer. This is done by adding a dimension to the view.

• Find the Customer Name dimension in the Data pane on the left.
• Drag Customer Name and drop it onto the Detail card within the Marks card.

That's it! As soon as you do this, the view will transform into a proper scatter plot. You'll now see hundreds of dots, where each one represents an individual customer. The horizontal position of a dot shows that customer's total sales, and the vertical position shows their total profit.

Taking Your Scatter Plot to the Next Level

A basic scatter plot is useful, but we can make it far more insightful by adding more layers of data through color, size, and other visual cues.

Add Context with Color and Size

Right now, all our dots are the same color and size. Let's change that to reveal more patterns.

Using Color for Categories

Let's say we want to know if customer profitability is related to a specific product category. We can use color to find out.

• Drag the Category dimension from the Data pane onto the Color card in the Marks shelf.

Instantly, your dots will be color-coded based on the primary product category the customer purchased from (Technology, Furniture, or Office Supplies). Now you can see if certain categories tend to be more or less profitable.

Using Size for Value

What if we also want to see which customers received the highest average discounts? We can use the size of the dots to represent this.

• Drag the Discount measure onto the Size card in the Marks shelf.

The marks will now change in size, with larger dots representing customers who have a higher sum of discounts. Hovering over the dots will show that a customer may have good profit, but if the dot is large, it suggests that profit could be even higher if a discount wasn't so aggressively used.

Add a Trend Line to See the Correlation

A trend line is a fantastic way to visualize the overall relationship direction in your data. It draws a line of best fit through your data points, making the correlation easier to see.

• Go to the Analytics pane (it’s a tab next to the Data pane on the left).
• Drag Trend Line from the pane and drop it onto the canvas. You'll see a box asking what kind of model to use. For now, just hover over and drop it on Linear.

Tableau will draw a line across your plot. If it slopes up, it indicates a positive correlation (in our example, as Sales increase, Profit tends to increase). A downward slope would mean a negative correlation. Hovering over the trend line gives you statistical information like the R-Squared and p-value, which tell you how well the line fits the data.

Improve Your Tooltips

The tooltip is the little box of information that appears when you hover over a data point. By default, it shows the variables already in the view. You can customize this to provide much richer information without cluttering the chart.

• Click on the Tooltip card in the Marks shelf.
• An editor box will appear. Here, you can type static text or use the "Insert" button to add other fields from your data source, like Region or Segment.
• This allows anyone viewing the chart to hover over an interesting point and get more context immediately.

Best Practices and Pro Tips

Here are a few quick tips to make your scatter plots even better and avoid common pitfalls.

• Handle Overlapping Points: When you have a lot of data points, they can overlap and hide one another (this is called "overplotting"). To fix this, click on the Color card and adjust the Opacity slider to make the marks semi-transparent. This helps reveal clusters of data that were previously hidden. You can also make the marks smaller by clicking the Size card.
• Use Filters: If your plot is too busy, try dragging a dimension (like Region or Year(Order Date)) to the Filters shelf. This allows you to focus on a smaller subset of your data at a time.
• Add Reference Lines for Quadrant Analysis: Go to the Analytics pane and drag a Reference Line onto your view. You can set it to the average for your X and Y axes, effectively dividing your chart into four quadrants: High Profit/High Sales, Low Profit/High Sales, etc. This is fantastic for segmentation.

Final Thoughts

Scatter plots are a fundamental and powerful visualization for any analyst. In Tableau, creating them is a simple process of placing two measures on your columns and rows, then breaking the view down with a dimension on the Detail card. From there, you can add layers of analysis with colors, sizes, and trend lines to uncover deep insights quickly.

While Tableau is an amazing tool for this kind of visual analysis, we recognize that the process of connecting data sources, creating dashboards, and making sense of the results can still involve a steep learning curve. At Graphed, we've designed an AI data analyst that streamlines this whole process. Imagine instead of clicking and dragging fields, you could simply type a question like, "create a scatter plot showing sales versus profit colored by region from our Shopify data" and have an interactive, real-time dashboard built for you in seconds. It allows anyone on your team to move straight to the insights, without getting stuck on the process.