Statistics Chapter 1: Graphing Distributions

Study Notes

This chapter covers methods for visualizing data distributions.
It includes concepts of individuals and variables, categorical and quantitative variables, histograms, stemplots, and time plots.
Statistics is the science of data. The initial step in working with data is organizing thoughts about the data.
An individual is an object of data. A variable is a characteristic of an individual.

Categorical variables classify individuals into groups (categories).
- Examples of categorical variables are breed (horse), stable, field of study (student).
Quantitative variables are numerical, and arithmetic operations make sense on them.
- Usually recorded with a unit of measurement (examples are selling price/dollar, weight/pound).

This is a process used to examine data using statistical tools and ideas to understand data.
The process starts by observing each variable independently. Then, relationships between variables are studied.
Visualizations (graphs) are explored first, then quantitative summaries.

The distribution of a variable shows the values the variable takes and how often it takes them.
- Categorical variables are represented using labels for categories and counts or percentages of individuals in each category.
Pie charts and bar graphs are used to illustrate distributions of categorical variables.

The distribution of a categorical variable details the categories and counts/percentages falling into each.
Pie charts display distributions as slices of a circle, sized by counts or percentages of categories.
Bar graphs show each category as a bar; bar heights indicate category counts or percentages.

Quantitative data distributions tell us the values the variable takes and how often it takes them. Visualizing quantitative data use histograms and stemplots.
Histograms use bars to show the distribution of a quantitative variable. Bar height represents the number of individuals with a value within a specific class.
Stemplots separate each observation into a stem and a leaf, plotting these together to show distribution, while maintaining original values

Histograms are suitable for visualizing quantitative variables with many values or large datasets.
Possible values are divided into equal-width classes.
Frequency of each interval is calculated.
- Frequency can also be expressed as percentages.
Bars display the distribution, where bar heights indicate the interval frequency

Examine the overall pattern and deviations.
- Overall pattern can be described in terms of shape, center, and spread.
Outliers, values deviating from the overall pattern, should also be identified.

Symmetrical distributions have approximately mirrored right and left sides.
Right-skewed distributions have a longer right tail than the left.
- Skewed left distributions have a longer left tail.

Stemplots arrange data by splitting each observation into a stem and a leaf.
Stems represent all digits of an observation except for the last (rightmost) digit.
Leaves represent the rightmost digit.
Stems are organized vertically, and leaves increase from the stem.