Describing Data with Tables and Graphs: Structured Study Notes

Describing Data with Tables and Graphs

Organizing Categorical Data

Categorical data refers to variables that can be divided into groups or categories, such as symptoms, blood types, or survey responses. Organizing this data helps us summarize and compare groups efficiently.

• Frequency Table: Lists each category and the number of observations in that category.

• Relative Frequency Table: Adds a column showing the proportion of observations in each category, calculated as the category's count divided by the total count.

• Two-way (Contingency) Table: Displays the frequency for each combination of two categorical variables.

Example: A clinic records the primary symptom reported by patients. The frequency table might look like:

Symptom	Frequency	Relative Frequency
Back pain	8	0.267
Fatigue	8	0.267
Headache	7	0.233
Nausea	5	0.167

Two-way Table Example: Symptoms by age group:

Age Group	Back pain	Fatigue	Headache	Nausea
0-19	2	2	1	1
20-59	5	5	5	3
60+	1	1	1	1

Additional info: Two-way tables are essential for examining relationships between categorical variables, such as age and symptom type.

Bar Charts and Pie Charts

Bar charts and pie charts are graphical methods for displaying categorical data. Each has distinct uses and design considerations.

• Bar Chart: Uses bars to represent the frequency or proportion of each category. Bars are separated to emphasize that categories are discrete.

• Pie Chart: Divides a circle into slices, each representing a category's proportion of the total. Best for showing parts of a whole.

Example: Distribution of blood types among donors:

Blood Type	Count	Proportion
O	46	0.460
A	36	0.360
B	18	0.180

Design Tips for Bar Charts:

• Start axis at zero.

• Use equal bar widths and clear labels.

• Avoid unnecessary decoration.

When to Use Bar vs. Pie Charts:

• Bar charts: Compare categories, especially when there are many or when exact values matter.

• Pie charts: Show proportions of a whole, best with few categories.

Clustered and Stacked Bar Charts: Useful for comparing multiple categorical variables. Clustered bars group categories side by side; stacked bars show composition within each group.

Organizing Quantitative Data

Quantitative data consists of numerical values that can be measured or counted. Organizing this data helps reveal patterns and distributions.

• Frequency Distribution: Table that divides the range of data into intervals (classes) and shows the count for each interval.

• Class Width: The difference between consecutive lower class limits.

• Relative Frequency: Proportion of observations in a class.

• Cumulative Frequency: Running total of frequencies up to a given class.

Example: Frequency distribution of cavities per patient:

Class	Frequency	Relative Frequency	Cumulative Frequency
0-1	3	0.25	0.25
2-3	4	0.33	0.58
4-5	2	0.17	0.75
6-7	3	0.25	1.00

Ogive: A graph of cumulative frequency or cumulative relative frequency versus class boundaries.

Histograms, Stem-and-Leaf Plots, and Dotplots

These graphical methods are used to visualize the distribution of quantitative data.

• Histogram: Uses adjacent rectangles to represent classes of a quantitative variable. The area of each bar is proportional to frequency.

• Stem-and-Leaf Plot: Displays actual data values, split into "stems" (leading digits) and "leaves" (final digits).

• Dotplot: Places a dot above a number line for each observation, useful for small datasets or showing clusters.

Example: Distribution of resting heart rates among individuals:

• Histogram shows the shape, center, and spread of the data.

• Stem-and-leaf plot allows you to see individual values and their distribution.

• Dotplot highlights clusters and outliers.

Choosing the Right Display: Use histograms for large samples, stem-and-leaf plots for moderate samples, and dotplots for small samples or when you want to see individual values.

Key Formulas

• Relative Frequency: $\text{Relative Frequency} = \frac{\text{Frequency of category}}{\text{Total frequency}}$

• Cumulative Frequency: $\text{Cumulative Frequency}_i = \sum_{j=1}^{i} \text{Frequency}_j$

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

Recap Table

Keyword/Concept	Definition or Note
Frequency table	Lists each category and the number of observations in that category.
Relative frequency table	Shows the proportion of observations in each category.
Two-way table	Displays frequencies for combinations of two categorical variables.
Bar chart	Displays categories using bars; bar length represents frequency or proportion.
Pie chart	Shows proportions of a whole using slices.
Histogram	Graph of adjacent rectangles for classes of a quantitative variable.
Stem-and-leaf plot	Displays actual data values split into stems and leaves.
Dotplot	Places dots above a number line for each observation.
Ogive	Graph of cumulative frequency or cumulative relative frequency.

Additional info:

• These notes cover the essential methods for describing and visualizing both categorical and quantitative data, including tables and graphical displays. Understanding these concepts is foundational for further statistical analysis.