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

Chapter 2: Exploring Data with Tables and Graphs

1. Frequency Distributions for Organizing and Summarizing Data

Frequency distributions are essential tools in statistics for organizing and summarizing data. They allow us to see patterns and trends by grouping data into tables or graphs.

• Frequency Table: Tallies (counts) the number of times a value appears in a dataset. Frequency tables often include cumulative frequency and relative frequency.

• Relative Frequency: The percentage of the total number of observations that falls into each category or class. It is calculated as: $\text{Relative Frequency} = \frac{\text{Frequency for a class}}{\text{Sum of all frequencies}}$

• Cumulative Frequency: The running total of frequencies up to a certain class or category.

Example Table:

Daily Commute Time in Los Angeles (minutes)	Relative Frequency
0-14	12%
15-29	38%
30-44	20%
45-59	16%
60-74	8%
75-99	2%

Key Points:

• Bins (intervals) must have the same width and not overlap.

• Frequency tables help summarize large datasets by grouping data into intervals.

1.1 Frequency Table Example: Commute Times in Boston

Commute times are grouped into intervals of 10 minutes. The frequency table shows the count, relative frequency, and cumulative frequency for each bin.

Bin (Minutes)	Frequency	Relative Frequency (%)	Cumulative Frequency
15-24	3	15.00	3
25-34	3	15.00	6
35-44	3	15.00	9
45-54	3	15.00	12
55-64	2	10.00	14
65-74	2	10.00	16
75-84	2	10.00	18
85-94	2	10.00	20

• Relative Frequency: Calculated as the percentage of the total number of commuters. For example, $3 \times 100 / 20 = 15\%$.

• Cumulative Frequency: A running total of frequencies.

Key Observations:

• Most commuters fall in the range of 15-64 minutes, covering 70% of the dataset.

• Longer commute times highlight potential areas of concern for transportation efficiency.

2. Relative Frequency Distribution

Relative frequency distributions replace class frequencies with relative frequencies (proportions or percentages). This allows for easier comparison between datasets of different sizes.

• Formula: $\text{Relative Frequency for a class} = \frac{\text{Frequency for a class}}{\text{Sum of all frequencies}}$

• Percentage for a class: $\text{Percentage for a class} = \frac{\text{Frequency for a class}}{\text{Sum of all frequencies}} \times 100\%$

The sum of percentages in a relative frequency distribution should be close to 100%.

Class Limits and Boundaries

• Lower Class Limit (LCL): Smallest value that can belong to a class interval. $\text{Lower Class Limit (LCL)} = \text{Smallest Value in a Class Interval}$

• Upper Class Limit (UCL): Largest value that can belong to a class interval. $\text{Upper Class Limit (UCL)} = \text{Largest Value in a Class Interval}$

• Class Midpoint (CM): Value halfway between the lower and upper class limits. $\text{Class Midpoint (CM)} = \frac{\text{Lower Class Limit} + \text{Upper Class Limit}}{2}$

• Class Boundaries (CB): Values that separate class intervals from each other. $\text{Class Boundaries (CB)} = \frac{\text{Upper Class Limit of Previous Class} + \text{Lower Class Limit of Next Class}}{2}$

Example:

• Class Interval: 10-19, 20-29, 30-39

• For 10-19: LCL = 10, UCL = 19, CM = $\frac{10+19}{2} = 14.5$, CB = $\frac{19+20}{2} = 19.5$ (Upper), $\frac{10+9}{2} = 9.5$ (Lower)

• For 20-29: LCL = 20, UCL = 29, CM = $\frac{20+29}{2} = 24.5$, CB = $\frac{19+20}{2} = 19.5$ (Lower), $\frac{29+30}{2} = 29.5$ (Upper)

3. Comparisons

Comparing two or more relative frequency distributions in one table makes data comparisons easier.

Commute Time (min)	NY, NY (%)	Boise, ID (%)
0-14	2.1	7.5
15-29	28.9	75.8
30-44	35.5	12.1
45-59	20.1	3.2
60-74	10.2	1.4
75-99	3.2	0.0

• Boise commute times are generally lower than New York's, with most commuters in Boise falling into the shortest time bins.

• Comparisons highlight differences in population density and transportation efficiency.

4. Histograms

A histogram is a graphical representation of the data from a frequency table. The x-axis contains the bins, and the y-axis contains the frequencies. Histograms are useful for visualizing the distribution, spread, and outliers in data.

• Definition: A histogram displays the shape of the distribution of the data.

• Important Uses:

  • Shows the location of the center of the data

  • Shows the spread of the data

  • Identifies outliers

4.1 Relative Frequency Histogram

Similar to a histogram, but the vertical scale is marked with relative frequencies instead of actual frequencies.

4.2 Common Distribution Shapes

• Normal Distribution: Bell-shaped histogram, indicating data are normally distributed.

• Uniform Distribution: All bins have approximately the same frequency.

• Skewed Distribution: Data are not symmetric and extend more to one side.

4.3 Skewness

Definition: Data are skewed if they are not symmetric and extend more to one side than the other.

• Positively Skewed (Right Skewed): Longer right tail.

• Negatively Skewed (Left Skewed): Longer left tail.

5. Graphs that Enlighten and Graphs that Deceive

Graphs are powerful tools for data visualization, but they must be used correctly to avoid misleading interpretations.

5.1 Graphs that Enlighten

• Dotplot: Plots each data value as a point above a horizontal scale. Useful for displaying the shape and distribution of data.

• Stemplot (Stem-and-Leaf Plot): Separates each value into a stem and leaf. Retains original data values and shows distribution.

• Time-Series Graph: Plots quantitative data collected at different points in time. Reveals trends over time.

• Bar Graph: Shows frequencies of categories of categorical data. Bars may be separated by small gaps.

• Pie Chart: Depicts categorical data as slices of a circle, with each slice proportional to the frequency count for the category.

5.2 Graphs that Deceive

• Graphs can be misleading if scales are manipulated or if visual elements exaggerate differences.

• Always check axis labels, scales, and proportions to ensure accurate interpretation.

Additional info: These notes expand on the original content by providing full definitions, formulas, and structured examples for each concept. All tables have been recreated and formulas are presented in LaTeX format for clarity.