I
n this chapter you’ll learn how to work with categorical data in the
form of tables and ordinal variables. You’ll learn how to use Excel’s
PivotTable feature to create tables, and you’ll explore how to analyze
these data in the table using StatPlus.PivotTables
In the previous chapter you used t tests and nonparametric tests to analyze
continuous variables. You can also apply hypothesis tests to categorical and
ordinal data. These type of data are most commonly seen in surveys, which
record counts broken down by categories. For example, you create a table
of instructors broken down by title (assistant professor, associate professor,
or full professor) and gender (male or female). Are there signifi cantly more
male full professors than female? How many female professors would you
expect given the data? An analysis of categorical data addresses questions of
this type.
To illustrate how to work with categorical variables, let’s look at data from
a survey of professors who teach statistics courses. The Survey workbook
includes 392 responses to questions about whether the course requires cal-
culus, whether statistical software is used, how the software is obtained by
students, what kind of computer is used, and so on. The workbook contains
the following variables shown in Table 7-1:Table 7-1 Survey of Statistics Professors Data
Range Name Range Description
Computer A2:A393 Computer used in the course
Dept B2:B393 Department
Available C2:C393 Type of computer system available to the student
Interest D2:D393 The amount of interest in a supplementary statistics text
Calculus E2:E393 The extent to which calculus is required for the course
Uses_Software F2:F393 Whether the course uses software
Enroll_A G2:G393 Categorical variable indicating semester course
enrollment in the instructor’s course (For example,
001-050 means that from 1 to 50 students are enrolled
each semester).
Enroll_B H2:H393 Categorical variable indicating annual course enrollment
Max_Cost I2:I393 Maximum cost for a supplementary computer text
276 Fundamentals of Statistics