Homework

1. Review. Get the output for Chapter 10, Figures 10-1 through 10-4, as described in the textbook, pp. 195-196, using data files on the CD that came with your textbook. As it is assumed that you are familiar with basic statistical topics like significance and association for crosstabs, this is not discussed in class but the homework is collected. The main purpose is to become comfortable with the process of obtaining SPSS output for data used in the textbook.

   Printing output: To export to Word and print, highlight Output at the top of the outline pane on the left, then right-click and select Export. Export as type HTML file (the instructor found on his setup that this worked better than using type Word/RTF). After saving, load the file into Word, select View, Print Layout; then Insert, Page Numbers, add your name, and print to bring to class.

2. Missing values analysis. Note: The Missing Values Analysis module is on VCL (http://vcl.ncsu.edu). At VCL, select "SPSS All Modules". Unlike the regular SPSS image on VCL, there are only 2 copies of the "All Modules" image, limiting use to two NCSU students at a time, so plan ahead (you may reserve ahead). A tutorial in VCL is here.
   
   Load aggregatedgss.sav from the Norusis dataset CD.
   Analyze, Missing Values Analysis
   Move all variables to the Quantitative Variables list
   Click the Patterns button, select "Tabulated cases", Continue
   Click the Descriptives button and check "t tests with groups formed by indicator variables" and check "include probabilities in table" In the Estimation area, check EM
   Click the EM button and check "Save completed data"
   Click File and name the new file aggregatedgss2.sav
   Save, Continue, OK
   

   Be prepared to discuss output in class. Not to turn in, but note how the output file has filled in missing values using the EM method.

   
   

3. The main focus of the class will be going over missing values analysis (MVA) and data imputation, and also on filtering your data to be sure that they meet such common statistical assumptions as linearity and homoscedasticity. Note: All data-based dissertations in this department must treat testing of assumptions and undertake MVA if appropriate. Unfortunately, the textbook does not cover this directly so there are no textbook exercises on it. Rely on the StatNotes readings and be prepared to discuss MVA and filtering topics in class.

Explore

• Questions and answers from prior years' texts, including for this week, can be found by clicking on Tabachnick and Fidell, Hutcheson, Tacq, Girden, Kline, or Byrne. This tip applies to subsequent weeks but is only listed here.

• SPSS Data Transformations and Selections