Unformatted text preview:

1Psychology 210L Statistical Methods Lab January 18, 2007 Lab #1: SPSS Data File Creation and Formatting Log onto your computer and open SPSS by clicking the SPSS icon that lives on the desktop (actual location may vary): An initial dialog box should appear asking you how you want to begin. Today, we’ll be creating a data file containing vital information about 14 liberal arts colleges. To begin the process, select “Type in Data” and click OK. Now you’re in the SPSS data editor. The spreadsheet is organized as a grid with columns and rows—data are entered in the cells on this spreadsheet (those of you who are familiar with Microsoft Excel will see some obvious parallels). In virtually all data files, individual cases are represented in rows. Each school (or “case”) represented in your file will have one row of data. Variables (different pieces of information about each case) are each represented in a different column.2 Let’s begin by defining a variable. First, note that the SPSS data editor actually consists of two spreadsheets; you’re currently viewing one of them, and the other is hidden behind it. In the bottom left corner of the window are two tabs (see below) that allow you to toggle between the data view and variable view spreadsheets. The former is where the data (the “numbers”) will be located. The latter provides a summary of the features of each variable. It’s certainly possible to enter data before specifying the desired features for each variable, but let’s be compulsive and define our variables first. It’s a slower way to start, but will save you some frustration in the long run. If you click the variable view tab, the spreadsheet will be subtly but magically transformed into the one you see at the right. This will allow us to specify some of the important characteristics of each variable. Strangely enough, each variable is now a row, whereas it used to be a column. Take a second to get your bearings and scan each column header to see what will define each variable. Quite logically, the first thing that SPSS wants is a name for the variable we’ve selected. Variable names in SPSS are limited to 8 characters. This can be somewhat obnoxious if you have variables with long names (handedness, occupation, etc). You’ll have to be creative, or use abbreviations. Not to worry though – you can provide a longer name under the column called label. Let’s start with our first variable, the name of each school – we’ll call it college. If you’re as paranoid about forgetting what it means as I am, type in “Name of College” in the label column. At this point, your screen should look something like the following: (note that the other columns are automatically filled with default values)3What do these other fields represent? I’m glad you asked (you might not want to mess with all of these for now, but keep this as a reference guide to use later on)... TYPE: Allows you to specify any special formatting that might be required. For example, some kinds of numbers like calendar dates and currency amounts have specific conventions for their representation: the raw input 80572 might become $805.72 or August 5, 1972 as would fit one’s needs. This option allows you to specify several such options, such as scientific notation and string (ie, as a string of arbitrary symbols devoid of any mathematical meaning). A college’s name is clearly a string of characters, so indicate “string” in the appropriate window. WIDTH: This is largely cosmetic. It specifies how many positions are shown for each piece of data in the data view window. If you specify 3, for instance, then a number like 2453 will be represented as 245 in the data view window. I usually leave this at the default unless I notice that my data are overrunning the window. For our first variable, you’ll eventually want to increase this so the names all fit (thanks a lot, Swarthmore.) DECIMALS: This specifies how many decimal places will be shown for each piece of data in the data view window. If you specify 2 decimals, then a value of 1.43379 will be truncated to 1.43. Similarly, a value of 1 would be extended to 1.00. The number of decimals is pretty much irrelevant for our first variable, but will be important later. LABEL: Again, this allows you to type in a description of your variable that is not limited to eight characters. It’s great for people with poor memories. Type in “Name of College”, just to be complete. VALUES: For categorical variables, this is where you specify names for each of the possible categories. For example, if sex was a variable, you could use this field to specify that the number “1” indicates “male” and “2” indicates “female”. Since each College name is different, it doesn’t make any sense to define categories – There’s only one school called Whitman, one called Carleton, etc. They’d each comprise their own unique category. Therefore, leave the current entry (“None”) as is. MISSING: If any data are missing (for instance, if a particular number is not available), you can specify a value that indicates the number is unaccounted for. I usually use something easily distinct, like “999”. If I then put 999 in my data set, SPSS will know to skip this entry, rather than interpret it literally as 999 (the number that comes before 1,000 and after 998). There’s probably no need to specify one for out College Name variable, since we know all of their names. COLUMNS: This specifies how wide each data column will appear in the data view window. If you have long numbers (or labels) for a variable, you might want to increase this from the default. If you want to conserve electrons or be able to fit more data on one screen, you can shorten it. Again, thanks to schools with long names, you’ll want to increase this to about 10.4ALIGN: This specifies how you want to align the values within each column in the data view window. Although I tend to select “Right,” feel free to choose the option you find the most aesthetically pleasing (peek back at the data view window to see the changes). MEASURE: Specifies the type of variable. You get three choices here: nominal, ordinal, and scale measurements. Here’s a little conceptual explanation of each: • Nominal: these are simply identifiers that have no mathematical meaning whatsoever. Things like a person’s


View Full Document

Whitman PSYCHOLOGY 210 - Laboratory

Download Laboratory
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Laboratory and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Laboratory 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?