Table of Contents (click to go directly to topic)
Datasets used in the workshop
In this workshop, we will use the "Big Class.jmp" dataset available in the "Help > Sample Data" directory in JMP:
- To open this dataset, go to
- Help>Sample Data>Examples for Teaching>Big Class
If you want to practice further with real data, the 2007-2008 National Health and Nutrition Examination Survey (NHANES) dataset is available. To download it, click NHANES_HCM757.jmp and choose to Save the dataset as NHANES_HCM757.jmp in a location or folder of your choice.
The "Help > Sample Data" directory in JMP contains several data tables from different domains, and some of these will also be used to illustrate examples.
- Open JMP by double-clicking the desktop icon
- Read the "Tip of the day"
- JMP Starter and JMP Menus
- Set Preferences
- Open existing data files of several types (JMP, Excel, and other…)
- Open the JMP dataset "Big Class"
- Help Menu
- Indexes: Statistics
- Books: JMP Introductory Guide and more…
- Sample Data
- The “?” tool (Note: this feature does not work on Macs with the Snow Leopard operating system)
- JMP User Community>JMP Blog
Exploring the Data Table
- Table attributes: Rows, columns, the 4 window panels, move columns, edit column names, resize, Column Info
- Modeling Type
- Data Type
- Enter data in a new JMP dataset
Sharing and Saving Your Work
- Copy and paste: Select graphs and sections of a report and copy paste into Word, PowerPoint, etc...
- Use Selection tool to select
- Then right-click>Copy or Edit>Copy
- In Word or Powerpoint (or other destination), Edit>Paste or Edit>Paste Special>Picture (Enhanced Metafile)
- Save your analysis in scripts for re-submission
Data Transformations (recoding, value labels, value ordering, formulas)
Right click on column or variable name → Column Info
- Recoding Values
- Value Labels
- Re-ordering Values
- Use formulas to calculate new columns
Step 1: Univariate Analysis: Distribution
Look at variables or data items (also called columns) individually and appraise and describe their validity.
- How are the variables distributed? Are there outliers? Are the outliers invalid data points? Are there corrections that should and can be made?
- Click on bars in graphics.
- Right click on points for options to inspect them further.
- Use lasso tool to choose a group of points.
- Video 8: Distribution platform
Step 2: Bivariate Analysis: Fit Y by X
Look at the data items or variables in relationship to each other.
- Analyze>Fit Y by X (This legend indicates on the lower left indicates the appropriate analysis based on the modeling type of the variables.)
- Look at the relationship between 2 continuous variables
- Look at the relationship between a continuous variables (Y) and a nominal variable (X)
- Look at the relationship between 2 nominal variables
- Look at the relationship between a nominal variable (Y) and a continuous variable (X)
Step 3: Multivariate Analysis: Fit model
- Analyze>Fit Model
Graph Menu (top bar)
Types of JMP Graphs
Help>Sample Data>Medical studies>Lipid data** The example graphs were made using the “Lipid” data:
Advanced graphic editing
Edit>Layout menu for more advanced graphics editing
Video 10: Graph Builder; Overlay Plots; Charts
Video 11: Scatterplot Matrix
Tables Menu (Subset, join, concatenate/append, stack, split, summarize/tabulate)
Video 13: Tabulate
- SAS-JMP Comparison
- See Column info in “NHANES_HCM757” dataset. Note SAS name and SAS label attributes