Chapter 2: Exploring Data with Tables and Graphs – Study Notes

Exploring Data with Tables and Graphs

Introduction

Chapter 2 focuses on the various methods for displaying and summarizing data visually and numerically. Understanding these displays is essential for interpreting data, identifying patterns, and communicating findings effectively. The main tools discussed include frequency tables, bar graphs, histograms, stem-and-leaf plots, and the interpretation of distribution shapes.

Key Considerations Before Displaying Data

• Purpose and Audience: The choice of display depends on the intended audience and the goals of the presentation.

• Data Characteristics: Consider the center (average), variation (spread), distribution, outliers (extreme values), and whether time is a relevant factor.

Tabular Data Displays

Frequency Distribution Table

A frequency distribution table lists each unique data value (or group of values) and the number of times it occurs in the dataset.

• Frequency: The count of occurrences for each value or category.

• Relative Frequency: The proportion or percentage of the total for each value or category.

Example: For a set of 20 test scores, the frequency and relative frequency for each score can be calculated as follows:

Score	Frequency	Relative Frequency
99	1	5%
90	3	15%
88	1	5%
84	4	20%
81	3	15%
79	2	10%
77	2	10%
73	2	10%
68	1	5%
51	1	5%

Additional info: The table above is inferred from the described process and may not match the exact original data values.

Grouped (Class) Frequency Distribution Table

Data can also be grouped into classes or categories (e.g., by grade ranges). Each class should have the same width for consistency.

Class (Score Range)	Frequency	Relative Frequency
90–99 (A)	4	20%
80–89 (B)	8	40%
70–79 (C)	6	30%
60–69 (D)	1	5%
50–59 (F)	1	5%

Key Components of Grouped Tables

• Lower Class Limit: The smallest value in a class.

• Upper Class Limit: The largest value in a class.

• Class Boundaries: Values that separate classes, often adjusted for rounding (e.g., 89.5 between 80–89 and 90–99).

• Class Midpoint: The average of the lower and upper class limits. Formula: $\frac{\text{Lower Class Limit} + \text{Upper Class Limit}}{2}$

• Class Width: The difference between consecutive lower (or upper) class limits. Formula: $\text{Class Width} = \text{Lower Class Limit of Class 2} - \text{Lower Class Limit of Class 1}$

Graphical Data Displays

Bar Graphs

Bar graphs use rectangles to represent the frequency or relative frequency of categories. The bars are separated by gaps, emphasizing that the categories are distinct.

• Common for categorical or discrete data.

• Gaps between bars indicate separate categories.

Dot Plots

A dot plot stacks dots for each data value, with each dot representing one observation. While similar to bar graphs, dot plots are less commonly used in professional settings.

Histograms

A histogram is similar to a bar graph but is used for quantitative data grouped into intervals (classes). The bars are adjacent (no gaps), reflecting the continuous nature of the data.

• Best for displaying the distribution of interval or ratio data.

• No gaps between bars; each bar represents a class interval.

Pareto Charts

A Pareto chart is a special type of bar graph or histogram where the bars are arranged from tallest to shortest (highest to lowest frequency). This format highlights the most significant categories.

Stem-and-Leaf Displays

A stem-and-leaf display splits each data value into a "stem" (all but the final digit) and a "leaf" (the final digit). This method preserves the original data values while showing the distribution.

• Stem: The leading digit(s) of each value.

• Leaf: The last digit of each value.

Example: For scores 73, 77, 79, the stem is 7 and the leaves are 3, 7, 9. The display would look like:

Stem	Leaf
5	1, 8
6	8
7	3, 3, 7, 7, 9, 9
8	1, 1, 4, 4
9	0, 0, 0, 9

To reconstruct the original data, combine the stem and leaf (e.g., 7 | 3 = 73).

Other Data Displays (Brief Overview)

• Pie Chart: Circular chart divided into sectors; not emphasized in this course.

• Scatter Plot: Plots paired (x, y) data; covered in detail in Chapter 10.

• Time Series Graph: Plots data points over time; useful when time is a variable of interest.

• Frequency Polygon: Uses class midpoints to plot frequencies as connected points.

• Ogive: Cumulative frequency graph using upper class limits.

Additional info: These displays are less emphasized for exam purposes but may be encountered in other contexts.

Distribution Shapes

Common Distribution Shapes

• Normal (Symmetric, Bell-Shaped): Data is evenly distributed around the center, forming a bell curve. Visual: Bars rise to a central peak and fall symmetrically.

• Uniform: All values occur with approximately the same frequency.

• Skewed Right (Positively Skewed): Most data is concentrated on the left, with a tail extending to the right (lack of data on the right).

• Skewed Left (Negatively Skewed): Most data is concentrated on the right, with a tail extending to the left (lack of data on the left).

Example: If most test scores are high with a few low outliers, the distribution is skewed left.

Summary Table: Main Data Displays

Display Type	Best For	Key Features
Frequency Table	All data types	Lists counts for each value or class
Bar Graph	Categorical/discrete data	Bars with gaps
Histogram	Continuous/interval data	Bars with no gaps
Stem-and-Leaf	Small to moderate datasets	Shows actual data values

Key Formulas

• Relative Frequency: $\text{Relative Frequency} = \frac{\text{Frequency}}{\text{Total Number of Observations}}$

• Class Midpoint: $\text{Class Midpoint} = \frac{\text{Lower Class Limit} + \text{Upper Class Limit}}{2}$

• Class Width: $\text{Class Width} = \text{Lower Class Limit of Next Class} - \text{Lower Class Limit of Current Class}$

Conclusion

Understanding and constructing tables and graphs is foundational for statistical analysis. Mastery of these displays enables clear communication of data patterns and supports further statistical inference in later chapters.