A Simple Data Table
In this book, we'll most often work with data that has already been entered and stored in a file, much like you would type and store a paper in a word-processing file or data in a spreadsheet file. In Chapter 2, you'll see how to create a data table on your own.
We'll start with the Michelson data mentioned earlier.
Click File → Open.
Navigate your way to the folder of data tables that accompany this book.[2]
[2] All of the data tables used in this book are available from support.sas.com/authors. If you are enrolled in a college or university course, your instructor may have posted the files in a special directory. Check with your instructor.
The data table appears in Figure 1.2. Notice that there are four regions in this window: three vertically arranged panels on the left, and the data grid on the right.
The three panels provide metadata (descriptive information about the data in the table). In addition to displaying the metadata, the entries in the panel are editable, so you can change metadata. Later we'll discuss these panels in greater detail. For now, let's just get oriented.
Beginning at the top left, we find the Table panel, which displays the name of the data table file as well as optional information provided by the creator of the table. You'll see a small red triangle pointing downward next to the table name.
|
Red triangles indicate a context-sensitive menu, and they are an important element in JMP. We'll discuss them more extensively a few pages from now, but you should expect to make frequent use of these little red triangles. |
Figure 1.2. The Michelson 1879 Data Table
Just below the red triangle, there is a note describing the data and identifying its source. You can open that note (called a Table variable) just by double-clicking on the words beginning "Source and background." Figure 1.3 shows what you'll see when you double-click. A table variable contains metadata about the entire table.
Figure 1.3. Table Variable Dialog Box
Below the Table panel is the Columns panel, which lists the column names and JMP modeling types, as well as other information about the columns. This will be explained further below, but for now, let's take note of a few important landmarks and concepts.
Figure 1.4. Columns Panel
The notation (2/0) in the top box of the panel tells us that there are two columns in this data table, and that neither of them is selected at the moment. In a JMP data table, we can select one or more columns or rows for special treatment. There is much more to learn about the idea of selection, and we'll return to it later in this chapter.
Next we see the names of the two columns. To the left of the names are icons indicating the modeling type. In this example, the blue triangle next to Velocity means that the column contains a continuous variable.
The green ascending bar icon next to Trial# indicates an ordinal variable. This data table doesn't include a nominal variable, but the corresponding icon looks like a red bar graph.
You'll also notice an asterisk next to the Trial# variable. This is one of several special symbols, which, in this case, indicates that the creator of the data table specified the order of values for this variable (first, second, third, and so on). If no order had been specified, JMP would sequence the values alphabetically.
Finally, we find the Rows panel (Figure 1.5), which provides basic information about the number of rows (in this case 100). Like the other two panels, this one provides quick reference information about the number of rows and their states.
|
The idea of "row states" is an important one in JMP, and probably will seem unfamiliar. It is fairly simple and quite useful, and is discussed more fully later in the chapter in the "Row States" section. |
The top row indicates that there are 100 observations in this data table. The next four rows refer to the four basic row states in a JMP data table. Initially, all rows share the same state, in that none has been selected, excluded, hidden or labeled. Row states enable us to control whether particular observations appear in graphs, are incorporated into calculations, or whether they are highlighted in various ways.
Figure 1.5. Rows Panel
The Data Grid area of the data table is where the data reside. It looks like a familiar spreadsheet format, and it just contains the raw data for any analysis. Unlike a spreadsheet, each cell in the data grid contains a data value, but never a formula. The data values might be the result from a computation, but we cannot place a formula directly into a cell. We can assign a formula to an entire column, but not to one cell.
In the upper-left corner of the data grid, you'll see the region shown here. There is a diamond-shaped disclosure button (with blue shading on the left side here in Windows; on a Macintosh it is an arrowhead 
). Disclosure buttons allow you to expand or contract the amount of information displayed on the screen. The disclosure button show here lets you temporarily hide the three panels discussed above.
Try it out! Click on the disclosure button to hide and then reveal the panels.
The red triangles offer you menu alternatives that won't mean much at this point, but which we'll discuss in the next section. The hotspot in the upper-right corner (above the diagonal line) refers to the columns of the grid, and the one in the lower-left corner to the rows.
The very top row of the grid contains the column names, and the left-most column contains row numbers. The cells contain the data.