Chapter 3: Constructing Graphical and Tabular Displays of Data

Constructing Graphical and Tabular Displays of Data (3.1)

Types of Variables

In statistics, understanding the types of variables is fundamental for selecting appropriate methods of data display and analysis.

• Categorical variable: Consists of names or labels that represent groups or categories of individuals. Examples include academic major, ZIP code, or gender (coded as 0 and 1).

• Numerical variable: Consists of measurable quantities that describe individuals, such as age or maximum speed of a car.

Example: Identifying Variable Types

• Age (in years) of a hip-hop artist: Numerical

• Academic major of a student: Categorical

• Maximum speed of a car: Numerical

• ZIP code of a home: Categorical

• Gender coded as 0 (man) and 1 (woman): Categorical

Frequency and Frequency Tables

Frequency tables are essential tools for summarizing categorical data.

• Frequency of a category: The number of observations in that category.

• Frequency table: A table listing all categories and their frequencies.

Definitions

• Frequency distribution of a categorical variable: The categories of the variable together with their frequencies.

• Relative frequency of a category: The proportion of all observations that fall in that category, calculated as:

$\text{Relative frequency} = \frac{\text{Frequency of the category}}{\text{Total number of observations}}$

Example: Frequency and Relative Frequency Table

Consider a class survey on favorite movie genres:

Category	Frequency	Relative Frequency
Drama	5	0.119
Action	6	0.143
Thriller	4	0.095
Comedy	16	0.381
Horror	5	0.119
Other	6	0.143
Total	42	1.000

• Largest relative frequency: Comedy (0.381 or 38.1%)

Relative Frequency Distribution

The relative frequency distribution of a categorical variable lists the categories together with their relative frequencies. The sum of all relative frequencies for a categorical variable is always 1.

Bar Graphs

Bar graphs are graphical representations of frequency or relative frequency distributions for categorical data.

• Frequency bar graph: Categories are displayed on the horizontal axis, frequencies on the vertical axis. Each bar's height corresponds to the frequency of the category.

Example: Constructing a Frequency Bar Graph

• List categories (e.g., movie genres) on the horizontal axis.

• Mark frequency values on the vertical axis.

• Draw bars above each category to represent its frequency.

Logical Operations with Categories: AND/OR

Logical operations such as AND and OR are used to identify subsets of data that meet specific criteria.

• AND: Selects data points that satisfy both conditions.

• OR: Selects data points that satisfy at least one condition.

Example: Calendar Dates

• Thursdays in November 2020: 5, 12, 19, 26

• Dates in the third week: 15, 16, 17, 18, 19, 20, 21

• Dates in the third week AND are Thursdays: 19

• Dates in the third week OR are Thursdays: 5, 12, 15, 16, 17, 18, 19, 20, 21, 26

Interpreting Multiple Bar Graphs

Multiple bar graphs allow comparison of proportions across different groups for each category.

• Proportion: The height of each bar represents the proportion of individuals in a group (e.g., men or women) who fall into a category (e.g., political party).

• Comparison: Compare proportions between groups for each category.

Example: Survey of Political Party Affiliation

• Proportion of women who are Democrats: 0.37

• Proportion of men who are Independents: 0.43

• Comparison: A smaller proportion of women (0.38) than men (0.43) identified as Independents.

• Absolute numbers: More women (411) than men (378) identified as Independents due to a larger sample of women.

• Sampling error: Survey results may not exactly represent the entire population due to sampling variability.

Important Note on Survey Interpretation

• Survey proportions apply only to the surveyed sample, not necessarily to the entire population.

• Sampling error can cause the true population proportion to differ from the sample proportion.

Additional info: These notes cover the foundational concepts of categorical and numerical variables, frequency and relative frequency tables, bar graphs, and logical operations in data categorization, as well as interpretation of graphical data displays. These are essential skills for introductory statistics students.