Which among the given graph is used to show the relationship between two variables or the development of variable over time?

When you were learning algebra back in high school, you might not have realized that one day you would need to create a scatter plot to demonstrate real world results.

Back in school, the examples we had to plot always seemed silly. Hours spent studying for a test versus the test grade received. The height versus weight of a group of people. Or the correlation between sales of hot coffee and the outside temperature.

But as a working adult (or maybe just a curious one), there are many times you may actually need to use that grade school math.

And creating a scatter plot is definitely one of those times. There are so many real world applications that a scatter plot offers that can help you or your audience to visualize data and what it means.

Let’s take you back to high school math for a second, because you very well may have left any and all knowledge of what a scatter plot is back at your doodled-on desk.

What is a Scatter Plot?

A scatter plot is a type of data visualization that shows the relationship between different variables. This data is shown by placing various data points between an x- and y-axis.

Essentially, each of these data points looks “scattered” around the graph, giving this type of data visualization its name.

Scatter plots can also be known as scatter diagrams or x-y graphs, and the point of using one of these is to determine if there are patterns or correlations between two variables.

Take a look at this example of a scatter plot pulled from one of Visme’s templates.

Customize this scatter plot template and make it your own!Edit and Download

The two variables are the square footage of a home versus its price. We pulled a sample data set of a couple handfuls of homes to see if we could determine a relationship between these two variables.

As the x-axis goes from the smallest size to the largest, we can see that there is a slight positive correlation showing that as square footage increases, so does the price.

Of course there could be other factors contributing to this, like location or recent renovations, but we can see from this scatter diagram that there is a correlation between the square footage and home cost.

The patterns or correlations found within a scatter plot will have a few different features.

• Linear or Nonlinear: A linear correlation forms a straight line in its data points while a nonlinear correlation might have a curve or other form within the data points.
• Strong or Weak: A strong correlation will have data points close together while a weak correlation will have data points that are further apart.
• Positive or Negative: A positive correlation will point up (i.e., the x- and y-values are both increasing) while a negative correlation will point down (i.e., the x-values are increasing while the corresponding y-values are decreasing).

However, if you don't see any of these features present within your graph, that means there’s no correlation between your data.

When To Use a Scatter Plot

Each type of chart or graph has its own rules for when it’s going to be the best data visualization to showcase your information.

Let’s dive into the best times to use a scatter plot to visualize your data set.

Use a scatter plot to determine whether or not two variables have a relationship or correlation.

Are you trying to see if your two variables might mean something when put together? Plotting a scattergram with your data points can help you to determine whether there’s a potential relationship between them.

Let’s say you’re running an ice cream business, and you’re curious to see if there's a pattern in why your sales have been low recently.

You might create a scatter plot to measure different factors, including outside temperature.

Customize this scatter plot template and make it your own!Edit and Download

You always want to plot your scatter diagram with both the x-axis and the y-axis increasing as they go out so that you can determine correlation.

As we can see in the above example, people tend to buy ice cream – a cold dessert – less often when the temperature is cold outside.

Use a scatter plot when your independent variable has multiple values for your dependent variable.

Okay, let’s take it back to math class for a minute and go over what independent and dependent variables mean.

First of all, a variable is the thing you’re trying to track or measure. Every graph has two variables – an independent variable that is typically graphed on the x-axis and a dependent variable that is typically graphed on the y-axis.

An independent variable is the controlled variable. This is what changes naturally, or what the person manipulating the experiment or graph changes.

A dependent variable is the variable that is being studied or measured. In the case of a scatter plot, it’s the variable that we’re looking to determine whether or not has a correlation with the independent variable.

If you’re trying to determine if height and weight have a correlation, the height will be placed on the x-axis and weight will be placed on the y-axis, like in the example below.

Customize this scatter plot template and make it your own!Edit and Download

Because weight fluctuates much more than height, it’s likely that you could have different weights for the same height in your data, giving you more than one dependent variable value for each independent variable.

Use a scatter plot when you have two variables that pair well together.

If you have two variables that pair well together, plotting them on a scatter diagram is a great way to view their relationship and see if it’s a positive or negative correlation.

For example, think about birth weight versus gestational age (how long the baby has been in utero). It would make sense that a baby who was able to grow inside its mother for longer would be larger, and therefore weigh more, correct?

Let’s take a look at this data on a scatter plot.

Customize this scatter plot template and make it your own!Edit and Download

As we would expect, the longer a baby is able to “cook,” the more it tends to weigh at birth.

Other examples of variables that appear to go hand in hand would be hours worked versus money made, time studied versus test grade or price versus diamond size.

When Not to Use a Scatter Plot

Just as there are certain times that it makes sense to use a scatter plot to visualize your data, there are a couple of examples when you want to stay away from this type of chart.

Avoid a scatter plot when your data is not at all related.

There are certain variables that make it obvious that there’s no correlation, therefore a scatter plot would be a useless way to visualize your information.

For example, if you’re gathering a random survey on a classroom full of students, putting together the students’ varying heights and the number of pets they have at home would make no sense on a scatter plot.

These two variables obviously have no relationship whatsoever, and while they can still be fun to graph, a bar chart (one for each data value) might be the better choice here.

Avoid a scatter plot when you have too large a set of data.

When you have so much data in your scatter plot that it clogs up the entire graph, this is the result of overplotting.

Statistician Nathan Yau sums up this phenomenon pretty well in the below graphic:

As another example, take a look at the scatter plot below. It’s so dense that it essentially becomes one large blob, and it’s hard to read much from this kind of diagram.

There are a few ways to counteract an overplotted scatter plot, though. First, consider using a heatmap that shows where the most point-heavy sections of your data are.

You could also color code various data sets, use translucent data points to create a heatmap-like effect and more.

However, your best bet is to avoid using a scatter plot when you have so much data that it becomes a large blob.

Things to Keep in Mind With a Scatter Plot

As you take a look at your data, there are a few things to keep in mind when you decide to use a scatter plot to determine relationships or correlation.

Correlation is not always causation.

Just because you might see a strong positive or negative correlation in your data does not necessarily mean that your independent variable is the reason your dependent variable is measuring the way it is.

These are correlations, meaning that it appears that your independent variable does have some sort of effect on your dependent variable.

Let’s jump back into our ice cream sales example.

While it may seem that the weather is the direct cause of a decrease in sales, there could be so many other factors that are leading to slower business.

Perhaps there was a natural disaster like a hurricane that led to a mandatory evacuation and therefore less business. A new ice cream shop could have opened down the street creating competition that wasn’t there before.

Some days people just don’t want to buy ice cream. And while, sure, the colder weather might be a factor, just because you see a correlation on a scatter plot does not mean you should take it as law.

You can have more than one dependent variable.

Your data set might include more than one dependent variable, and you can still track this on a scatter plot.

The only thing you’ll want to change is the color of each dependent variable so that you can measure them against each other on the scatter plot.

Let’s take a look back at our height versus weight example.

In that scatter plot, we added two different dependent variables – male and female – to see if there was also a difference between those factors. We colored female points orange and male points brown so that we could differentiate between the two.

This is another great way to avoid overplotting. Ensuring you’re color coding your data helps to set it apart so that you can see more of your points.

How to Create a Scatter Plot With Visme

Now that you know all about what a scatter plot is and when you do and don’t want to use one, let’s get started with our tutorial on how you can actually create one.

There are 16 different chart types you can create right in Visme, and a scatter plot is only one of them! Learn more about how to get started below.

1. Start with a template.

There are several different starter scatter plot templates available right in Visme for you to jump into and start adding your data.

Browse through our selection and click on the one you want to use. This will take you to the Visme dashboard with this template right inside so that you can immediately start customizing it to fit your needs.

Create your scatter plot View more templates

2. Input your data.

Click on the scatter plot, and the graph settings will appear along the left side of your editor. Click Chart Data to input your data.

The x-axis information will go in the top row and the corresponding y-axis data will go in the bottom row. Be sure that all of your numbers on the x-axis are in numerical order from lowest to highest.

If you have more than one dependent variable, simply add that information to the next row for a second variable, the fourth row for a third and so on.

You can also head over to the Import Data tab to import data you’ve already gathered in a Google Sheet or Excel file.

3. Label your axes.

Head over to Settings, the third tab in the chart settings. Click to open the Axis tab. This is where you can customize your x- and y-axis information and ensure your scatter plot data is appearing correctly.

The first thing you need to do is ensure that Treat labels as text is switched to Off, otherwise your scatter plot will look a bit more like a line chart with dots.

Give each axis a label dictating what the variable is and customize your fonts to match the rest of your design by clicking the gear icon next to each axis. Or, as you see here, you can use separate text areas to label your graph.

Check out our article on font pairing to determine the best ones to use.

4. Color code.

You can fully customize every single part of your scatter plot in Visme’s editor. Choose a color for each of your dependent variable’s points, choose a color for your values, your axes and your chart title.

Click on the colored box next to each variable or each label in your settings to access the color picker. Choose from colors you’ve used in the past and preset palettes, or click on the + sign to access Visme’s color picker.

Once you find colors that make sense for your content or your overall design, you can move onto the next step.

5. Animate your scatter plot.

Last but not least, animate your scatter diagram! Animation comes with any type of graph or chart within Visme’s editor.

This is a fun way to create interactive content if you’re embedding your scatter plot onto a webpage (like the one below) or sharing a link with your audience.

There are five different animation types for you to choose from for your chart: Linear, Bounce, Elastic, Ease Out and Ease In.

Once you’ve completed your changes, simply click outside of the chart on your canvas, then you can download your scatter plot or share it online however you like.

Your Turn

Ready to start plotting your own scatter plot? Check out Visme’s graph maker for yourself and start creating one of 16 different charts to help visualize your information.

Be sure to check out all of the scatter plot templates available to jumpstart your design, as well. We’re just here to make graph-making and graphic design easier for you.