Essential Graphing • Graph Builder • Example Using Graph Builder
Previous
 • 
Next
Example Using Graph Builder
You have data about nutrition information for candy bars. You want to find out which factors can best predict calorie levels. Working from a basic knowledge of food science, you believe that the fat content is a good place to start.
1.
Select Help > Sample Data Library and open Candy Bars.jmp.
2.
Select Graph > Graph Builder.
3.
Drag and drop Total fat g into the X zone.
4.
Drag and drop Calories into the Y zone.
Example of Calories versus Total fat g
As you suspected, the candy bars with higher fat grams also have higher calories. But the relationship is not perfect. You can add other factors to try to increase the correlation. Next, determine whether cholesterol has an effect.
5.
Drag and drop Cholesterol g into the Group X zone.
Example of Calories versus Total fat g by Cholesterol g in the Group X Zone
Eight levels of the variable make the graph difficult to read. Try putting Cholesterol g into the Wrap zone instead.
6.
Click on Cholesterol g in the Group X zone and drag and drop it into the Wrap zone.
Example of Calories Versus Total fat g by Cholesterol g in the Wrap Zone
A scatterplot of Calories versus Total fat g is created for every level of Cholesterol g.
You can see that some of the cells have very little data; other cells have a lot of data. Among the cells that have a lot of data (cholesterol equals 0, 5, 10), there is still considerable variation in calories. So you decide to remove Cholesterol g.
7.
Remove Cholesterol g by right-clicking on the Cholesterol g label in the Group X zone and selecting Remove.
Next, determine whether carbohydrates have any effect.
8.
Drag and drop Carbohydrate g into the Wrap zone.
Example of Calories Versus Total fat g by Carbohydrate g
Carbohydrate g is a continuous variable with many values, so Graph Builder uses the percentiles to create five ranges of carbohydrate g levels. About the same number of points are displayed in each group. You can see that the relationship between calories and fat is relatively strong for each level of carbohydrate. It appears that carbohydrates adds additional predictive ability.
Now that you have determined that carbohydrates have a significant impact on calories, combine the five scatterplots into one scatterplot to directly compare the lines. You still want to identify the carbohydrate levels.
9.
Drag and drop the Carbohydrate g label from the Group X zone to the Overlay zone.
Example of Carbohydrates Overlay
The scatterplots combine into one, and the carbohydrate levels are individually colored.
Modify the legend title.
10.
Right-click on the legend title (Carbohydrate g) and select Legend Settings.
11.
Rename the Title to Carbohydrate grams.
12.
Click OK.
Note: For details about making changes to the legend, see Modify the Legend.
13.
Now that you are satisfied with this graph, click Done.
Example of a Completed Graph
You now have a presentation-friendly graph that you can copy and paste outside of JMP.
To copy the entire graph:
14.
Click the Selection Tool .
15.
Click anywhere on the Graph Builder title bar.
The entire area is highlighted and ready to copy.
Launch Graph Builder
Launch Graph Builder by selecting Graph > Graph Builder.
The Graph Builder Window
Note: Any rows that are excluded in the data table are also hidden in the Graph Builder.
The Graph Builder window contains the following components:
•
Graph area and zones. See The Graph Area and Zones.
•
Element properties panel. Options vary depending upon the selected element type. See Right-Click Menu for a Graph.
•
Variables list, populated with the columns from the open data table. For details about the options in the red triangle menu, see the Using JMP book.
•
Buttons. See Buttons.
•
Element type icons. See Element Type Icons.
The Graph Area and Zones
The primary element in the Graph Builder window is the graph area. The graph area contains drop zones, and you can drag and drop variables from the Select Columns box into the zones. The following table describes the Graph Builder drop zones.
X, Y
Drop variables here to assign them the X or Y role.
Group X
Subsets or partitions the data based on the variable or variables that you select. Displays the variable horizontally. Once a variable is placed here, no variable can be placed in Wrap.
Group Y
Subsets or partitions the data based on the variable or variables that you select. Displays the variable vertically.
Map Shape
Drop variables here to create map shapes. See Create Map Shapes. If you have a variable in the Map Shape zone, the X and Y zones disappear.
Wrap
Subsets or partitions the data based on the variable or variables that you select. Wraps the data horizontally and vertically. Once a variable is placed here, no variable can be placed in Group X.
Freq
Drop a variable here to use it as a frequency or weight for graph elements that use statistics, such as mean or counts.
Overlay
Groups the Y variables by the selected variable, overlays the responses, and marks the levels with different colors.
Color
Drop variables here to color the graph:
•
If you are using a map, the map shapes are colored. See Change Map Colors and Transparency in Create Maps.
•
If you are using a contour plot, colored contours appear.
•
If your graph contains points, they are colored.
Tip: You can show or hide color using the Variables menu in the element properties panel.
Size
(Use with Map Shapes) Scales map shapes according to the size variable, minimizing distortion.
Page
Drop the By group variable to the Page zone to display each level of the group on a separate graph.
Legend
Shows descriptions of graph elements. If you attempt to drop a variable here, the variable defaults to Overlay. See Modify the Legend.
If you drop variables into the center area, JMP guesses the drop zone to put them into, based on whether the variables are continuous, ordinal or nominal.
•
The X, Y, and Map Shape zones are positional, and influence the types of graph elements that are available.
•
The Group X, Group Y, Wrap, and Overlay zones partition the data into subsets and lay out multiple graphs by either dividing the graph space or by overlaying the graphs.
•
The Color and Freq zones modify certain graph elements.
Related Information 
For the X, Y, Group X, and Group Y zones, see also:
•
Add Variables
•
Change Variable Roles
•
Remove Variables
•
Add Multiple Variables to Grouping Zones
Element Type Icons
You can change the element type by clicking on an element type icon. Use the SHIFT key to apply multiple elements at once. Once you select an element, only compatible elements are active.
Choose from the following element types:
The Points element shows data values.
The Smoother element shows a smooth curve through the data. The smoother is a cubic spline with a default lambda of 0.05 and standardized X values. You can change the value of lambda using the slider.
The Line of Fit element shows a linear regression with confidence intervals. The confidence intervals are fixed at 5% confidence, with an alpha of 0.05.
The Ellipse element shows a bivariate normal density ellipse.
The Contour element shows regions of density or value contours. If you specify only one continuous variable for X or Y, a violin plot appears instead of a contour plot.
The Line element shows a response summarized by categories.
The Bar element shows a response summarized by categories.
The Area element shows a response summarized by categories.
The Box Plot element shows a compact view of a variable’s distribution, with quartiles and outliers.
The Histogram element shows a variable’s distribution using binning. If you specify the same variable for X and Y, then the Y role is ignored and a single histogram appears.
Tip: To overlay histograms transparently, assign a Y variable and an Overlay variable. Then, click the Histogram element icon.
The Heatmap element shows counts using color for X and Y categories.
Tip: Hover over a cell to see tool tips that show labels.
The Pie element shows portions of a whole.
The Treemap element shows a response summarized by categories.
The Mosaic element shows counts using size for X and Y categories.
The Caption Box element shows a summary statistic value for the data.
The Formula element shows a function defined by a column formula.
The Map Shapes element creates a map on the graph.
When applicable, properties for each element appear and can be adjusted in the Graph Builder window. For more information, see Right-Click Menu for a Graph.
Buttons
There are three buttons on the Graph Builder window:
•
Undo reverses the last change made to the window.
•
Recall populates the Graph Builder window with the last graph that you created. The Recall button becomes the Undo button once you perform an action.
•
Start Over returns the window to the default condition, removing all data and graph elements from the window, and all variables from the drop zones.
•
Dialog opens the Graph Builder launch window. After you click it, the Dialog button becomes the Start Over button.
•
Done hides the buttons and Select Columns box and removes all drop zone outlines. In this presentation-friendly format, you can copy the graph to other programs. To copy the graph, select Edit > Copy. To restore the window to the interactive mode, click Show Control Panel on the Graph Builder red triangle menu.