From Data to Insight in Visual Analytics - How do you spot the cars that truly deliver value?

3 Likes

What makes a car a good buy? Is it the price, the performance, the fuel efficiency — or the right balance between all three?

This report explores these questions using SAS Visual Analytics and the SASHELP.CARS dataset, turning raw data into a clear, interactive story about the car market.

The analysis unfolds across three pages:

Overview – key KPIs and price segmentation
Fuel efficiency – distribution patterns and trade-offs
Value focus – comparing price against performance

To go beyond the standard visuals, a custom Value Score and a dynamic Top Car indicator are calculated directly in the Data pane — pinpointing the vehicle that delivers the strongest overall value.

Along the way, you'll pick up practical techniques for building dashboards that don't just display data — they tell a story.

Part 1 A First Glance: Understanding the Market – The Overview

The story begins with a simple, yet powerful overview page that provides an immediate understanding of the car market.

1.1 Page layout

The page is built using two Standard containers from the Objects pane, stacked vertically to create a clear and structured flow. This ensures consistent sizing and alignment of all visual elements across the page.

At the top, a descriptive Text object introduces the page: "Car Market Overview – Price, Performance and Distribution", setting clear context for the user from the start.

1.2 Key values

In the top Standard container, three key values provide a clear snapshot of the overall market:

Average Price: $33K
Average Highway Fuel Efficiency: 27 MPG
Average Horsepower: 216

These were created using Key value objects from the left pane, allowing aggregated measures to be shown clearly without unnecessary visual noise.

To make the values meaningful, aggregations were changed from sum to average in the Data pane, and each measure was renamed with an "Average" prefix for clarity.

A few design refinements completed the look:

Measure values were styled with a consistent color (#9EC1A3) via the Options pane.
The container height was reduced to free up space for the detailed visuals below. This was done by selecting the container in the Outline pane to highlight it, then clicking the handle at the bottom center of the container in the layout and dragging it upward.

1.3 Market Distribution – Treemap

Below the key values, a Treemap object shows how vehicles are distributed across price categories. It is placed inside a Precision container within the Standard container, allowing objects to be layered and positioned exactly where needed. The Treemap displays the number of cars in each category, where several calculations were required to ensure correct category definitions and labeling:

1. The first step was to define the Price Category item using Calculated item in the Data pane (Data - New data item - Calculated item):

2. To accurately represent the number of vehicles, a few preparation steps were required. A frequency measure was first created by assigning a value of 1 to each row (Calculated frequency), allowing counts to be aggregated correctly. An aggregated measure (Sum Freq) was then defined based on this frequency:

3. Next, a new dataset was created using “New data from aggregation” - located in the Data pane next to the dataset name (). Price Category and Sum Freq were then selected:

4. To support clear labeling in the Treemap, an additional Calculated item was added (Label Price Category Freq):

With this setup, the following Roles were assigned in the right pane:

Tile: Label Price Category Freq
Size: Sum Freq

The design was further refined in the Options pane to improve readability:

A Custom title: “Number of Cars by Price Category”.
Data labels styled in white for stronger contrast.
Removal of the Legend to reduce visual clutter.

To create a clear and intuitive visual distinction, Display Rules were applied in the right pane, as illustrated in the image below:

The following color scheme was used:

High-end: #2F5597
Mid-range: #5B87C5
Budget: #9DC3E6

💡 Key insights:

Budget cars dominate slightly.
High-end vehicles still represent a significant share of the market.

1.4 Adding Context with an Information Icon

To enhance usability, an information icon (ⓘ) was added next to the Treemap title, made possible by the Precision container. When clicked, it opens a Pop-up page explaining the price categories:

This approach consisted of:

Creating a new page with a Text object describing the categories.
Setting a background color (#F9EDC6) in the Options pane.
Change the page type to Pop-up by clicking the three dots next to the page name and selecting Page type → Pop-up.
Adding an Image object next to the title and uploading an information icon (ⓘ).
Link the icon to the Pop-up page by clicking the three dots on the image and selecting Add link → Page link.

1.5 Price Differences Across Vehicle Types – Bar chart

The analysis was further extended by comparing prices across different vehicle types. A grouped Bar chart was positioned next to the Treemap, with the following roles defined in the Roles pane:

Category: Type
Measure: Average Price (MSRP)
Group: Price Category

To maintain visual consistency, Display Rules were applied in the right pane. Since this chart uses a different variable than the Treemap (Label Price Category Freq), the same rules needed to be recreated to ensure the color scheme remains aligned across visuals:

A Custom title was also added to the Bar chart: “Average Price by Car Type and Price Category.”

💡 Key insights:

Sports cars dominate the high-end segment, with significantly higher prices than all other vehicle types.
SUVs, sedans, wagons, and trucks show a consistent price progression from budget to high-end.

The chart enables clear, side-by-side comparison, making differences between vehicle types and price segments easy to interpret at a glance.

Part 2 Fuel Efficiency: Distribution and Reality

The story then introduces Fuel Efficiency as a key dimension, explored on the next page of the report. This section provides a deeper view of how efficiency varies across vehicles and how it relates to performance.

2.1 Page layout

The page is structured using two Standard containers from the Objects pane, stacked vertically. This creates a clear separation between distribution insights and relationship analysis.

2.2 Fuel Efficiency Distribution – Bar chart

In the top container, a horizontal Bar chart visualizes fuel efficiency distribution. To support this, a new Calculated item was created in the Data pane to group vehicles into meaningful fuel efficiency categories:

The chart was configured by defining the following roles in the right pane:

Category: Fuel-Efficiency Category
Measure: Frequency

While the groupings differ from those on the first page, Display Rules reuse the same color scheme to keep the report visually consistent:

💡 Key insights:

Most vehicles fall into the mid-efficiency category.
High-efficiency vehicles are less common.
Low-efficiency vehicles make up the smallest segment.

2.3 Adding Context and Guidance

Instead of using a separate information image as on the previous page, additional context is integrated directly into the layout through a Text object placed above the Bar chart. The title, “Fuel Efficiency Analysis – Category Distribution and Performance”, was enhanced by embedding an information symbol (ⓘ) directly within the text. This creates a more seamless and intuitive user experience, where guidance is naturally part of the design rather than a separate element. To implement this, the following steps were performed:

Insert the desired symbol in Microsoft Word using the Segoe UI Emoji font (Insert → Symbol).
Select the symbol (ⓘ) and copy it.
Paste the symbol directly into the Text object in SAS Visual Analytics.

A separate Pop-up page was created, following the same approach as on the first page and to provide a more detailed explanation of the fuel efficiency categories:

The information symbol was linked to this Pop-up page by double-clicking the ⓘ in the title, then choosing and Add page link.

This approach provides users with easy access to additional context when needed, while keeping the main view clean, focused, and free from visual clutter.

2.4 Relationship Analysis – Scatter plot

To further explore relationships in the data, the analysis continues with a Scatter plot from the Objects pane and placed in the Standard container below. The following roles were assigned in the Roles pane:

Measures:

Horsepower (x-axis)
Highway Fuel Efficiency (MPG) (y-axis)

Color: Fuel Efficiency Category

This configuration allows each vehicle to be plotted individually, making it possible to observe patterns and relationships across the dataset.

The design was refined in the Options pane by adding the Custom title “How Efficiency Categories Relate to Horsepower and MPG”, and applying consistent Display Rules to represent the different fuel efficiency categories. To improve readability, the container was slightly enlarged, ensuring the visualization has enough space to clearly convey the patterns.

💡 Key insights:

Fuel efficiency decreases as horsepower increases.
Mid-efficiency vehicles dominate the central cluster.
High-efficiency vehicles are almost exclusively found at lower horsepower levels.

This visualization highlights one of the most fundamental trade-offs in the car market, the balance between performance and efficiency, and shows how scatter plots can reveal underlying relationships in the data.

Part 3 Value Matters: Price vs. Performance

The next page shifts the focus to whether higher cost actually delivers better performance and which vehicles offer the best return for money.

3.1 Page layout

This page is structured using two Precision containers, ensuring precise positioning and allowing objects to be layered cleanly on top of each other.

3.2 Price vs. Performance Segmentation of Vehicles – Pie chart

The analysis begins with an overview of how vehicles are distributed across price–performance categories, combining the previously defined price and fuel efficiency groupings. To enable this, a new Calculated item (Price vs. performance) was created in the Data pane, grouping vehicles into segments like this:

A Pie chart was added to the left of the top Precision container, with the following Roles assigned in the right pane:

Category: Price vs. performance
Measure: Frequency

Design refinements in the Options pane included:

Adding a Custom title: “Price vs. Performance Segmentation of Vehicles”.
Displaying data labels as percent of total.

To ensure consistent and meaningful use of colors across all visualizations, Report Display Rules were applied from the left pane. This not only improves visual consistency but also makes it easier for users to recognize and interpret categories across different charts.

To provide additional context, an Information icon (Image object) was placed next to the title and linked to a Pop-up page explaining each category, following the same approach used on the first page. This keeps the main view clean while still offering deeper insight when needed.

💡 Key insights:

Out of 428 vehicles, the majority fall into the medium value segment.
High price does not always equal high value.
Only a smaller portion of vehicles deliver strong value for money.

3.3 From Overview to Detail – List table

To support deeper exploration, a List table was added from the Objects pane and placed in the top Precision container to the right of the Pie chart. The table was configured by defining the following relevant items in the Roles pane:

Make
Model
Vehicle Type
Average Price
Average Horsepower
Average Highway Fuel Efficiency (MPG)
Price Category
Price vs. performance

The table automatically inherits colors from the Report Display Rules, ensuring visual consistency across the page. A Custom title, “Vehicle Overview: Price, Performance and Efficiency,” was added for clarity in the Options pane.

This interactive table allows users to drill down into the data and validate patterns observed in the visualizations.

3.4 Relationship Between Price and Performance – Scatter plot

To further explore value, a Scatter plot was introduced to visualize the relationship between price and horsepower, configured with the following roles defined in the Roles pane:

Measures:
- Price (x-axis)
- Horsepower (y-axis)
Color: Price vs. performance

By coloring the data points based on the Price vs. performance categories, the scatter plot not only shows the overall correlation, but also highlights how different value segments are distributed across the Price vs. Performance spectrum. This makes it easier to identify which vehicles truly stand out in terms of value.

Only one minor refinement was made in the Options pane, by adding a Custom title: “Relationship Between Price and Performance (Horsepower).” Thanks to the consistent use of Report Display Rules, colors are automatically aligned with the other visuals on the page.

💡 Key insights:

Higher price usually means higher performance — but not better value.
Best value = strong performance at a lower price.
Some high-priced cars still rank as low value.
The right balance between cost and performance is key.

3.5 Highlighting the Top Car

As a final touch, a dynamic Top Car indicator was created to highlight the vehicle with the highest value score. This was built through a series of structured steps:

1. First, a Value Score was created in the Data pane using Calculated item (Data - New data item - Calculated item):

2. Next, the score was aggregated to find the highest-scoring model (Top Value Score):

3. A new aggregated dataset was generated by selecting New data from aggregation next to the dataset name (), including the following:

4. The aggregated dataset was merged with the original data using the Model variable, producing a new dataset called Top Model Cars.

In the new dataset, additional calculations (Calculated item) were needed to isolate and describe the Top Car:

5. A Score Label:

6. Identification of the Top Car (type and model):

This gives the following results:

7. A label for the Top Car (Label Car):

8. Finally, all calculations were brought together into one variable used for display (Top Car price vs. performance):

A Key Value object was placed to the right of the scatter plot with the following roles:

Measure: Top Value Score
Lattice category: Top Car price vs. performance

For a cleaner look, unnecessary labels (Measure label, Measure value, and Lattice category label) were removed in the Options pane. An advanced filter was applied to ensure only the Top Car is displayed:

The final output is a clear visual highlight, showing the Top Car and its value score directly in the page:

Conclusion: A Data Story That Drives Insight

This report shows how SAS Visual Analytics can turn a simple dataset into a guided analytical journey — from a quick market overview, through efficiency trade-offs, to a deeper understanding of true value. The real strength lies not in the charts themselves, but in how they’re built and connected.

Key techniques that made the biggest difference:

Precision containers for layering icons and fine-tuned layouts
Calculated items to define custom categories and a Value Score
Report Display Rules for consistent colors across all visuals
Pop-up pages with info icons (ⓘ) to add context without clutter
"New data from aggregation" to power the dynamic Top Car indicator

Together, these small choices turn a collection of charts into a clear, interactive story — one that doesn’t just show data, but helps people understand and act on it.

Try these techniques on your own data and see how quickly numbers can turn into decisions. 🙌