Exploring Data with Tables and Graphs: Frequency Distributions and Data Visualization

Exploring Data with Tables and Graphs

Introduction

Organizing and summarizing data is a foundational skill in statistics. Frequency distributions and graphical representations help reveal patterns, trends, and differences within data sets, making large amounts of information more understandable and useful for analysis.

Frequency Distributions for Organizing and Summarizing Data

Definition and Purpose

• Frequency Distribution (or Frequency Table): A table that shows how data are partitioned among several categories (or classes) by listing each category along with the number (frequency) of data values in each.

• Purpose: To organize large data sets, making it easier to see the distribution and identify patterns such as clusters, gaps, or outliers.

Key Terms

• Lower class limits: The smallest numbers that can belong to each class.

• Upper class limits: The largest numbers that can belong to each class.

• Class boundaries: Numbers used to separate classes, eliminating gaps between class limits.

• Class midpoints: The value in the middle of each class, calculated as $(\text{Lower class limit} + \text{Upper class limit}) / 2$.

• Class width: The difference between two consecutive lower class limits (or boundaries).

Procedure for Constructing a Frequency Distribution

1. Select the number of classes (usually between 5 and 20).

2. Calculate the class width:

   • Formula: $\text{Class width} = \frac{\text{Maximum value} - \text{Minimum value}}{\text{Number of classes}}$

   • Round up to a convenient number.

3. Choose the first lower class limit (often the minimum value or a convenient value below it).

4. List the lower class limits by adding the class width successively.

5. Determine the upper class limits for each class.

6. Tally each data value into the appropriate class and count the frequencies.

Example: Commute Time in Los Angeles

• Suppose we want to organize daily commute times using 7 classes.

• Calculate class width, round up for convenience (e.g., from 12 to 15 minutes).

• Start lower class limits at 0, then add 15 for each subsequent class: 0, 15, 30, 45, 60, 75, 90.

• Upper class limits: 14, 29, 44, 59, 74, 89, 104.

• Tally and count frequencies for each class.

Relative Frequency Distributions

Definition and Calculation

• Relative Frequency Distribution: Each class frequency is replaced by a relative frequency (proportion) or percentage.

• Calculation: $\text{Relative frequency} = \frac{\text{Class frequency}}{\text{Sum of all frequencies}}$

• The sum of all relative frequencies (as percentages) should be close to 100% (allowing for rounding errors).

Comparisons Using Relative Frequency Distributions

• Combining two or more relative frequency distributions in one table allows for easy comparison between data sets.

• Example: Comparing commute times in New York, NY and Boise, ID shows that Boise has a much higher proportion of short commute times, reflecting differences in city size and population density.

Cumulative Frequency Distributions

Definition and Use

• Cumulative Frequency Distribution: The frequency for each class is the sum of the frequencies for that class and all previous classes.

• Useful for determining how many data values fall below a particular value.

Critical Thinking: Understanding Data Distributions

Normal Distributions

• In a normal distribution, frequencies start low, increase to a maximum, then decrease, forming a symmetric pattern.

• Frequencies before and after the maximum should be roughly mirror images.

Gaps in Data

• The presence of gaps in a frequency distribution may indicate data from two or more different populations.

• Example: A frequency distribution of penny weights shows a gap, suggesting two populations: pennies made before 1983 (mostly copper) and after 1983 (mostly zinc).

Tables

Example: Comparing Relative Frequency Distributions

The following table compares the relative frequency distributions of commute times in New York, NY and Boise, ID:

Commute Time (min)	New York, NY (%)	Boise, ID (%)
0-14	10.2	45.3
15-29	18.7	30.5
30-44	35.1	15.2
45-59	20.0	6.0
60+	16.0	3.0

Additional info: Table values are illustrative; actual values may differ based on the original data.

Summary

• Frequency distributions and their variants (relative, cumulative) are essential for summarizing and comparing data.

• Key terms include class limits, boundaries, midpoints, and width.

• Critical analysis of distributions can reveal underlying patterns, such as normality or the presence of multiple populations.