SPSS Statistics for Data Analysis and Visualization by Keith McCormick & Jesus Salcedo & Jon Peck & Andrew Wheeler

Author:Keith McCormick & Jesus Salcedo & Jon Peck & Andrew Wheeler
Language: eng
Format: epub
ISBN: 9781119003663
Publisher: Wiley
Published: 2017-04-11T00:00:00+00:00

Figure 9.1 Culture and sport perceptual map

Contains public sector information licensed under the Open Government Licence v3.0. (https://www.nationalarchives.gov.uk/doc/ open-government-licence/version/3/)

Starting with Crosstabs

Now let’s get to work in SPSS Statistics. We will be using a modified version of the LeRoux and Rouanet dataset. Our version is different in two ways from other versions you may find: The Multiple Imputation feature of SPSS Statistics has been used to replace the missing Income values, and AutoRecode has been used to replace the string values with numeric values and labels. The version of the data that we will be using is called Taste_Imputed.sav, which is available on the book’s website.

We will begin with Correspondence Analysis. The trick in selecting appropriate variables for this technique is to remember a couple of key points. First, Correspondence Analysis allows just two variables: a row variable and a column variable. Second, the whole point of the technique is to display on two dimensions information that otherwise would be difficult to display on two dimensions. So, if you only have a 2x2 crosstabulation matrix you don’t need it. Also, if you have strong linear associations between two ordinal variables you can probably visualize that with less effort. The variables most appropriate will be a pair of nominal variables with several categories. While there is no rule that we must pair a demographic variable with a behavioral variable, it is an approach that is quite common. For instance, if you are a film studio, you might want to know which demographic patterns are associated with film attendance. While it might also be quite interesting to relate film preference with concert attendance, it might not be as immediately actionable as the demographics. With this in mind, we will set up the Crosstabs menu with TV, Film, Art, and Eat in rows, and Income and Age in Columns (Figure 9.2).

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.