Creating the Data Appendix

The Data Appendix you are going to create will serve as a codebook or user’s guide for the final data file analysis.sav. People can look at the Data Appendix and learn about all your variables. It is a document you compose yourself, using whatever word-processing software you choose. When you save the Data Appendix, you will give it the name data-appendix.doc (but use whatever the appropriate suffix is for your word processing program). Ultimately, you might want to save it as PDF so anyone can read it.

You will need to create a new syntax file so that you can record the commands you use to create the Data Appendix. Open a new window (make sure any other syntax windows are closed).

The Data Appendix should consist of multiple sections, or “entries,” one for each of the variables in the final data set. For this exercise, it is okay to just create entries for the variables you are going to use. This is not normal practice however—you would normally include entries for all the variables in the dataset.

For each of the variables, the entry in the codebook should give:

1. The name of the variable.

2. The number of missing observations, in the format m/n, where m represents the number of missing observations and n represents the total number of observations (missing plus non-missing).

3. A definition or explanation of the variable.

4. The possible values of the variable.

5. The coding of the values; i.e., an explanation of what each value of the variable represents.

6. A table showing the frequency distribution and the percent frequency distribution. If the variable is ordinal or interval level, you should also include a cumulative percentage column.

7. A bar chart (for nominal or ordinal variables) or a histogram (for interval variables) that illustrates the percent frequency distribution.

If you are not sure what your data appendix should look like, you can click here to see a sample data appendix entry I created.

The Data Appendix you prepare for this assignment should consist of similar entries for the five other variables in the final data set (race3m1, race3m2, race3m3, race3m4, and Q16).

Make sure that you copy all the syntax that produced the frequency distribution and bar chart into your new syntax file. Add in comments so you remember what the code does later.

Name your syntax file dataappendix.sps, save it, and put it in your Command-Files folder. Save data-appendix.doc in your Documents folder