Aaron Poh

Step by Step / Updated 03-27-2016

After defining your variables and entering your data in SPSS Statistics, you may want to check that you have names defined for all your actual ordinal and nominal values, and that you have defined the correct measures for them. SPSS can help by scanning your data, finding values for which you don't have definitions, and pointing them out in a friendly way. The following steps use an existing file to walk through a demonstration:

Step by Step / Updated 03-27-2016

Here's a procedure you can follow to read data from a simple text file into SPSS. The file is named awards.txt. It contains two cases (rows of data) as two lines of text, with the data items in the two lines separated by spaces.

Article / Updated 03-26-2016

The Paired-Samples T Test in SPSS Statistics determines whether means differ from each other under two conditions. For example, you can use this test to assess whether there are mean differences when the same group of people have been assessed twice, such as when determining if an intervention had an impact by using a before and after design. The use of the Paired-Samples T Test is not limited to situations in which a group of people have been assessed at two time points. You can also use this test when a group has been assessed only once. For example, a group may have been asked to provide ratings on two products; in this situation, researchers can determine if one product was rated higher (preferred) than the other. The following figure shows the Paired-Samples T Test dialog box. Here, you can determine the change between current salary and beginning salary; so, in this example, you have data for one group of people that have been assessed twice (once when they were hired [beginning salary]) and currently [current salary]). Completed Paired-Samples T Test dialog box. In the next figure, under the Mean column, you can see the mean difference in salary between current and beginning salary. In this case, you can see that the mean difference between the two conditions is $17,403.81. You now need to determine if the difference between the means is significantly different or if the difference you’re seeing is just due to chance. The T column displays the actual result of the T Test and the DF column tells IBM SPSS Statistics how to determine the probability of the T statistic. The Sig. (2-Tailed) column tells the probability of the null hypothesis being correct. In the case of the Paired-Samples T Test, the null hypothesis is that the two means are equal; the alternative hypothesis is that the two means differ. If the probability value of the null hypothesis is very low (less than 0.05), you can conclude that the means are significantly different from each other. In the following figure, you can see that there are significant differences between the means, so employees are earning significantly more income now than when they first started working for this company. Paired Samples Test table.

Article / Updated 03-26-2016

SPSS has its own format for storing data and writes files with the .sav extension. This file format contains special codes and usually can't be used to export your data to another application. It's used only for saving SPSS data that you want to read back into SPSS at a later time. Several example files in this format are copied to your computer as part of the normal SPSS installation. These files can be found in the same directory as your SPSS installation. You can load any one of them by choosing File→Open→Data and selecting the file to be loaded. When you do so, the variable names and data are loaded and fill your SPSS window. If you have SPSS filled with data, you can save it to a .sav file by choosing File→Save As and providing a name for the file. Or if you've loaded the information from a file, or you've previously saved a copy of the information to a file, you can simply choose File→Save to overwrite the previous file with a fresh copy of both variable definitions and data. It's easy to be fooled by the way the SPSS documentation uses the word file. If you have defined data and variables in your program, the SPSS documentation often refers to it all as a "file," even though it may have never been ­written to disk. SPSS also refers to the material written to disk as a file, so watch the context. When you write your file to disk, if you don't add the .sav extension to the filename, SPSS adds it for you. When you choose File→Open→Data to display the list of files, you may or may not see the extension on the filename (it depends on how your Windows system is configured), but it's there.

Article / Updated 03-26-2016

If you choose to output a Word document file from your SPSS data, you have no graphic options to set because both text and graphics are included in one output file. The options you can choose from are shown here: whether to include all layers of any tables that may be in the output, whether to include footnotes and captions, and how models are to be handled. The choices you have in producing a Word ­document. The Page Setup for Export button opens a dialog box that allows you to lay out the page size and margins of the output. It makes it possible to specify wrapping and shrinking to make things fit. When you want to produce output, click Continue in the Export Output dialog box, and the file is generated. Then you can load the output file directly into Word, as shown here. SPSS output as a Word/RTF file. In this example, the output filename is wordfile, so the output file was named wordfile.doc. If the output file is in rich text format (RTF), it can be loaded and used by most word processors, including OpenOffice, StarOffice, and WordPerfect.

Article / Updated 03-26-2016

Writing data from SPSS is easier than reading data into SPSS. All you do is choose File→Save As, select your file type, and then enter a filename. You have lots of file types to choose from. You can write your data not only in two plain-text formats, but also in Excel spreadsheet format, three Lotus formats, three dBase formats, six SAS formats, and six Stata formats. If you’ll be exporting data from SPSS into another application, find out what kinds of files the other application can read, and then use SPSS to write in one of those formats. A second form of output from SPSS is an image. If you’ve generated a graphic that you want to insert into your word processor or place on your website, SPSS is ready to help you do it. SPSS Statistics Viewer displays graphs onscreen. From the SPSS Statistics Viewer, you can export images (and do some other things, too). Here’s how: Produce a graph or table. You can use any of the examples in Part IV to produce a graphic display. The SPSS Statistics Viewer window pops up and displays the output. Choose File→Export. The Export Output window appears. These selections control what gets output and into what format. In the Objects to Export section, select which items to include in the output. You can elect to have all objects output, all visible objects output, or only the ones you’ve selected. The visibility of an object refers to whether its name appears in the list — if you collapse the list so a particular name can’t be seen, the item is not visible. You can select items by clicking the items themselves, or by selecting their names in the list on the left. In the Document section, from the Type drop-down list, choose an output format. Your choices vary according to what you decided to output as specified at the top of the window. Here’s a list of the possible options: Excel 97–2004 (*.xls): Excel files can include text, tables, and graphics, with the graphics embedded in the 97–2004 workbook. The data can create a new file or be added to an existing workbook. No graphic options are available. Excel 2007 and higher (*.xlsx): Excel files can include text, tables, and graphics, with the graphics embedded in the 2007 and higher workbook. The data can create a new file or be added to an existing workbook. No graphic options are available. Excel 2007 and higher macro enabled (*.xlsm): Excel files can include text, tables, and graphics, with the graphics embedded in the 2007 and higher macro-enabled workbook. The data can create a new file or be added to an existing workbook. No graphic options are available. HTML (*.htm): HTML files can be used for text both with and without graphics. If graphics are included, those will be exported separately, and they’ll be included as HTML links. The graphic file type must also be chosen. Web Reports (*.htm or *.mht): Creates an interactive document that is compatible with most browsers, including Cognos Active Report. Portable Document Format (*.pdf): PDF documents exported will include not only text but also any graphics existing in the original. No graphics options are available. PowerPoint (*.ppt): PowerPoint documents can be written as text with the graphics embedded in the TIFF format. No graphic options are available. Text-Plain (*.txt): Text files can be output with graphic references included, and the graphics written to separate files. The reference is the name of the graphic file. The graphic file format is specified by choosing options in the lower section of this window. Text-UTF8 (*.txt): UTF-8 is Unicode text encoded as a stream of 8-bit characters. Graphics are handled the same as they are for text files. Text-UTF16 (*.txt): UTF-16 is Unicode text encoded as a stream of 16-bit characters. Graphics are handled the same as they are for text files. Word/RTF (*.doc): Word documents are written in rich text format (RTF), which can be copied into a Word document. No graphic options are available. None: When selected, this option means no text is output — only graphic images. The graphic file format is specified by options in the lower section of this window. In the Graphics section, select the image file format, if one is needed, from the Type drop-down list. You may be asked to select a format for your image file(s). You can select from .png, .bmp, .emf, .eps, .jpg, or .tif. Click the Browse button, select the directory and root filename, and click Save. Depending on what you chose to output, the actual output may be ­multiple files, and they’ll all have names derived from the root name you provide. The Save button doesn’t write the file(s) — it only inserts your selected name into the Export Output window. Click OK. The file(s) are written to disk — each in the chosen format, at the chosen location.

Article / Updated 03-26-2016

Calendar and clock arithmetic can be tricky, but SPSS can handle it all for you. Just enter the date and time in whatever format you specify, and SPSS converts those values into its internal form to do the calculations. Also, SPSS displays the date and time in your specified format, so it's easy to read. SPSS understands the meaning of slashes, commas, colons, blanks, and names in the dates and times you enter, so you can write the date and time almost any way you'd like. If SPSS can't figure out what you've typed, it clears away what you typed and waits for you to type something again. Internally, SPSS keeps all dates as a positive or negative count of the number of seconds from a zero date. Here's a bit of trivia for you. The zero date in SPSS is the birth of the Gregorian calendar in 1582. No kidding! You can choose a display format that includes or excludes the time, but the information is always there. You can even change the display format without loss of data. If the time isn't included in the data you enter, SPSS assumes zero hours and minutes (midnight). You determine the data type for each variable on the Data View tab of the Data Editor window. The type is chosen from the list of types shown here. On the right, you select a format. SPSS uses this format to interpret your input and to format the dates for display. Select the data type and the ­format. SPSS uses the format you select for both reading your input and formatting the output of dates and times. The Columns setting of the date variable on the Variable View tab of the Data Editor window is important. The column width determines the maximum number of characters that can be displayed. If you choose a format that is too narrow to fit, the date will show up only as a row of asterisks. The available formats are defined as a group and change according to the variable type. For example, the Dollar type has a different list of choices from those offered for the Date type. The list of format definitions you have to choose from are constructed by combining the specifiers listed here. Format definitions look like mm/dd/yy and ddd:hh:mm. Specifiers in Date and Time Formats Specifier Means dd A two-digit day of the month in the range 01, 02, . . . , 30, 31. ddd A three-digit day of the year in the range 001, 002, . . . , 364, 365. hh A two-digit hour of the day in the range 00, 01, . . . , 22, 23. Jan, Feb, . . . The abbreviated name of the month of the year, as in JAN, FEB, . . . , NOV, DEC. January, February, . . . The name of the month of the year, as in JANUARY, FEBRUARY, . . . , NOVEMBER, DECEMBER. mm When adjacent to a dd specifier in a format, a two-digit month of the year in the range 01, 02, . . . , 11, 12. When adjacent to an hh specifier in a format, a two-digit specifier of the minute in the range 00, 01, . . . , 58, 59. mmm A three-character name of a month, as in JAN, FEB, . . . , NOV, DEC. Mon, Tue, . . . The abbreviated name of the day of the week, as in MON, TUE, . . . , SAT, SUN. Monday, Tuesday, . . . The name of the day of the week, as in MONDAY, TUESDAY, . . . , SATURDAY, SUNDAY. q Q The quarter of the year, as in 1 Q, 2 Q, 3 Q, or 4 Q. Ss Following a colon, the number of seconds in the range 00, 01, . . . , 58, 59. Following a period, the number of hundredths of a second. ww WK The one- or two-digit number of the week of the year in the range 1 WK, 2 WK, . . . , 51 WK, 52 WK. Note: Although week numbers can be either one or two digits, the numbers always line up when printed in columns because SPSS inserts a blank in front of single-digit numbers. yy A two-digit year in the range 00, 01, . . . , 98, 99. The assumed first two digits of the four-digit year this represents are determined by the configuration found at Edit → Options → Data. yyyy A four-digit year in the range 0001, 0002, . . ., 9998, 9999. You can go back and change the format of a date variable at any time without fear of losing information. For example, you could enter the data under a format that accepted only the year, month, and day, and then change the format to something that contains only the hours and minutes. The format may not display all the information you entered (in fact, in this case, it won't), but when you change the format back to something more inclusive, all your data is still there. To enter data, choose a format — any format — that contains all the data you have. You can later change to a more limited format that displays only the information you want. But you can't go the other way. If you later choose a format that doesn't leave parts out, you see the defaults that were inserted by SPSS when you entered the data.

Article / Updated 03-26-2016

You start entering data into SPSS Statistics in the Data Editor. You use the Variable View tab of the Data Editor window to define the characteristics of your variables. Columns column The Columns column is where you specify the width of the column you'll use to enter the data. The folks at SPSS could have used the word Width to describe it, but they already used that term for the width of the data itself. A better name may have been the two words Column Width, but that would have been too long to display nicely in this window, so they just called it Columns. To specify the number of columns, select a cell and enter the number. Align column The Align column determines the position of the data in its allocated space, whenever the data is displayed for input or output. The data can be left-aligned, right-aligned, or centered. You've defined the width of the data and the size of the column in which the data will be displayed; the alignment determines what is done with any space left over. When you select a cell in the Align column, a list appears and you can choose one of the three alignment possibilities, as shown here. Aligning to the left means inserting all blanks on the right; aligning to the right inserts all the extra spaces on the left; centering the data splits the spaces evenly on each side. Values can be justified right or left, or positioned in the center. Measure column Your value here specifies the measure of something in one of three ways. When you click a cell in the Measure column, you can select one of these choices: Ordinal: These numbers specify the position (order) of something in a list. For example, first, second, and third are ordinal numbers. Nominal: Numbers that specify categories or types of things. You can have 0 represent "Disapprove" and 1 represent "Approve." Or you can use 1 to mean "Fast" and 2 to mean "Slow." Scale: A number that specifies a magnitude. It can be distance, weight, age, or a count of something. The type of measurement being made by the values in this variable.

Article / Updated 03-26-2016

The Values column in the SPSS Variable View tab is where you assign labels to all the possible values of a variable. If you select a cell in the Values column, a button with three dots appears. Clicking that button displays the dialog box shown here. You can assign a name to each possible value of a variable. Normally, you make one entry for each possible value that a variable can assume. For example, for a variable named Sex you could have the value 1 assigned the label "Male" and 2 assigned the label "Female." Or, for a variable named Committed you could have 0 for "No," 1 for "Yes," and 2 for "Undecided." If you have labels defined, when SPSS displays output, it can show the labels instead of the values. To define a label for a value: In the Value box, enter the value. In the Label box, enter a label. Click the Add button. The value and label appear in the large text block. To change or remove a definition, simply select it in the text block and make your changes; then click the Change button. Repeat Steps 1–4 as needed. Click OK to save the value labels and close the dialog box. You can always come back and change the definitions using the same ­process you used to enter them. The dialog box will reappear, filled in with all the definitions; then you can update the list. Sometimes you have a whole bunch of strings and you really don't want to make them all values because it seems like it'll be a lot of work. A variable like college major is a good example. If you dread setting up 1 as "Astrophysics," 2 as "Biology," 3 as "Chemistry," and so on, you can use a special dialog box called Automatic Recode (under the Transform menu) and it'll do all the work for you.

Article / Updated 03-26-2016

On the SPSS Statistics Variable View tab, the third column provides a spot to set the width for your variables and the fourth column is where you indicate the number of digits that appear to the right of the decimal point when the value appears onscreen. Width and Decimal settings on the Variable View tab. The width setting in the definition of a variable determines the number of characters used to display the value. If the value to be displayed is not large enough to fill the space, the output will be padded with blanks. If it's larger than you specify, it will either be reformatted to fit or asterisks will be displayed. Certain type definitions allow you to set a width value. The width value you enter as the width definition is the same as the one you enter when you define the type. If you make a change to the value in one place, SPSS changes the value in the other place automatically. The two values are the same. At this point, you can do one of three things: Skip this cell and accept the default (or the number you entered ­previously under Type). Enter a number and move on. Use the up and down arrows that appear in the cell to select a numeric value. The number of decimals is the number of digits that appear to the right of the decimal point when the value appears onscreen. This is the same number that you may have specified as the Decimal Places value when you defined the variable type. If you entered a number there, it appears here as the default. If you enter a number here, it changes the one you entered for the type. They're the same. Now you can do one of three things: Skip this cell and accept the default (or the number you entered earlier under Type). Enter a number and move on. Use the up and down arrows that appear in the cell to select a numeric value.