Describing Data with Tables and Graphs: Organizing Qualitative and Quantitative Data

Organizing Qualitative Data

Introduction

Qualitative data refers to categorical information that can be classified based on attributes or characteristics. Organizing such data is essential for meaningful analysis and interpretation. This section covers methods for summarizing and displaying qualitative data.

• Qualitative (Categorical) Data: Data that classifies individuals based on attributes or characteristics (e.g., color, religion, blood type).

• Frequency: The number of observations within a category.

• Relative Frequency: The proportion or percentage of observations within a category, calculated as: $\text{Relative Frequency} = \frac{\text{Frequency}}{\text{Total Number of Observations}}$

Example: Blood Type Distribution

Given the blood types of 25 army inductees, a frequency and relative frequency table can be constructed:

Blood Type	Tally	Frequency	Relative Frequency
O	|||||	5	0.20
A	|||||	5	0.20
B	|||||	5	0.20
AB	|||||	5	0.20
O	|||||	5	0.20

Additional info: The table above is inferred for illustration; actual tallies may differ.

Graphical Representations of Qualitative Data

Bar Graphs

Bar graphs display the frequency or relative frequency of categories using rectangular bars. The height of each bar represents the value for each category.

• Useful for comparing categories.

• Bars may be vertical or horizontal.

Pareto Charts

Pareto charts are bar graphs with bars arranged in decreasing order of frequency or relative frequency.

• Helps identify the most significant categories.

Side-by-Side Bar Graphs

Used to compare two or more sets of data, such as survival rates by ticket class on the Titanic.

Class	Survived	Total	Percent Survived
First	197	322	61.2%
Second	94	272	34.6%
Third	151	709	21.3%

Pie Charts

Pie charts display the proportion of each category as a sector of a circle. Each sector's angle is proportional to its relative frequency.

• Useful for showing parts of a whole.

• Angle calculation: $\text{Sector Angle} = \text{Relative Frequency} \times 360^\circ$

Organizing Quantitative Data

Introduction

Quantitative data consists of numerical measurements. Organizing such data involves grouping values into classes and displaying them using appropriate graphs.

• Discrete Data: Data with countable values.

• Continuous Data: Data that can take any value within a range.

Histograms

Histograms use adjacent bars to show the frequency of data within intervals (classes).

• Class: Groupings into which data are separated.

• Lower Class Limit: Smallest value in each class.

• Upper Class Limit: Largest value in each class.

• Class Width: Difference between lower class limits of consecutive classes. $\text{Class Width} = \text{Upper Class Limit} - \text{Lower Class Limit}$

Example: Number of Televisions in a Household

Given a data set, construct a frequency histogram using specified class limits and widths.

Stem-and-Leaf Plots

Stem-and-leaf plots display quantitative data by splitting each value into a "stem" (all but the last digit) and a "leaf" (last digit).

• Useful for small data sets.

• Preserves original data values.

Additional Displays of Quantitative Data

Time-Series Plots

Time-series plots show how a variable changes over time. Each point represents a value at a specific time.

• Useful for identifying trends and patterns.

Example: Money Spent by Consumers on Valentine's Day

Year	Amount
2007	2500
2008	2600
2009	2700
2010	2800
2011	2900
2012	3000

Graphical Misrepresentation of Data

Introduction

Graphs can be misleading if not constructed properly. This section discusses common pitfalls and guidelines for creating accurate and informative graphics.

• Misleading Graphs: Occur when scales are manipulated or data is omitted.

• Guidelines:

  • Label axes and provide units.

  • Minimize chartjunk (unnecessary decorations).

  • Use appropriate scales and avoid truncating axes.

  • Choose the correct graph type for the data.

  • Avoid using three-dimensional effects that distort perception.

Example: SAT Math Scores Over Time

Bar graphs that do not start at zero or omit axis labels can mislead viewers. Time-series plots are preferred for displaying changes over time.

Extra Problems

Practice with Histograms and Relative Frequency

Given a data set, students are asked to:

• Create a frequency histogram with specified number of classes.

• Construct histograms with given class limits and widths.

• Calculate relative frequencies.

• Describe the shape of distributions.