Chapter 1
Statistics: The Art and Science of
Learning from Data
 Learn
….
What Statistics Is
Why Statistics Is Important
Agresti/Franklin Statistics, 1 of 33
Chapter 1
 Learn…
How Data is Collected
How Data is Used to Make
Predictions
Agresti/Franklin Statistics, 2 of 33
Section 1.1
How Can You Investigate using Data?
Agresti/Franklin Statistics, 3 of 33
Health Study

Does a low-carbohydrate diet
result in significant weight loss?
Agresti/Franklin Statistics, 4 of 33
Market Analysis

Are people more likely to stop at a
Starbucks if they’ve seen a recent
TV advertisement for their coffee?
Agresti/Franklin Statistics, 5 of 33
Heart Health

Does regular aspirin intake
reduce deaths from heart
attacks?
Agresti/Franklin Statistics, 6 of 33
Cancer Research

Are smokers more likely than nonsmokers to develop lung cancer?
Agresti/Franklin Statistics, 7 of 33
To search for answers to
these questions, we…

Design experiments

Conduct surveys

Gather data
Agresti/Franklin Statistics, 8 of 33
Statistics is the art and
science of:



Designing studies
Analyzing data
Translating data into knowledge and
understanding of the world
Agresti/Franklin Statistics, 9 of 33
Example from the National Opinion
Center at the University of Chicago:


General Social Survey (GSS) provides
data about the American public
Survey of about 2000 adult Americans
Agresti/Franklin Statistics, 10 of 33
Example from GSS: Do you
believe in life after death?
Agresti/Franklin Statistics, 11 of 33
Three Main Aspects of
Statistics

Design

Description

Inference
Agresti/Franklin Statistics, 12 of 33
Design

How to conduct the experiment

How to select the people for the
survey
Agresti/Franklin Statistics, 13 of 33
Description

Summarize the raw data

Present the data in a useful format
Agresti/Franklin Statistics, 14 of 33
Inference

Make decisions or predictions based
on the data.
Agresti/Franklin Statistics, 15 of 33
Example from GSS: On a typical day,
about how many hours do you
personally watch television?
Agresti/Franklin Statistics, 16 of 33
What percentage of the people
surveyed reported watching 0 hours
of TV a day?
Agresti/Franklin Statistics, 17 of 33
Example: Harvard Medical School
study of Aspirin and Heart attacks

Study participants were divided into
two groups
• Group 1: assigned to take aspirin
• Group 2: assigned to take a placebo
Agresti/Franklin Statistics, 18 of 33
Example: Harvard Medical School
study of Aspirin and Heart attacks



Results: the percentage of each group
that had heart attacks during the study:
0.9% for those taking aspirin
1.7% for those taking placebo
Agresti/Franklin Statistics, 19 of 33
Example:
MedicalSchool
School
Example:Harvard
Harvard Medical
study
andHeart
Heart
attacks
studyof
ofAspirin
Aspirin and
attacks

Can you conclude that it is beneficial
for people to take aspiring regularly?
Agresti/Franklin Statistics, 20 of 33
Section 1.2
We Learn About Populations Using
Samples
Agresti/Franklin Statistics, 21 of 33
Subjects

The entities that we measure in a
study

Subjects could be individuals,
schools, countries, days,…
Agresti/Franklin Statistics, 22 of 33
Population and Sample

Population: All subjects of interest

Sample: Subset of the population for
whom we have data
Agresti/Franklin Statistics, 23 of 33
Example Format
•
•
•
•
•
Picture the Scenario
Question to Explore
Think it Through
Insight
Practice the concept
Agresti/Franklin Statistics, 24 of 33
Example: The Sample and the
Population for an Exit Poll

In California in 2003, a special election
was held to consider whether Governor
Gray Davis should be recalled from
office.

An exit poll sampled 3160 of the 8 million
people who voted.
Agresti/Franklin Statistics, 25 of 33
Example: The Sample and the
Population for an Exit Poll
Example: The Sample and the Population for an Exit Poll

What’s the sample and the
population for this exit poll?

The population was the 8 million
people who voted in the election.
The sample was the 3160 voters who
were interviewed in the exit poll.

Agresti/Franklin Statistics, 26 of 33
Descriptive Statistics

Methods for summarizing data

Summaries usually consist of graphs
and numerical summaries of the data
Agresti/Franklin Statistics, 27 of 33
Types of U.S. Households
Agresti/Franklin Statistics, 28 of 33
Inference

Methods of making decisions or
predictions about a populations
based on sample information.
Agresti/Franklin Statistics, 29 of 33
Parameter and Statistic

A parameter is a numerical
summary of the population

A statistic is a numerical summary
of a sample taken from the
population
Agresti/Franklin Statistics, 30 of 33
Randomness

Simple Random Sampling: each
subject in the population has the
same chance of being included in that
sample

Randomness is crucial to
experimentation
Agresti/Franklin Statistics, 31 of 33
Variability

Measurements vary from person to
person

Measurements vary from sample to
sample
Agresti/Franklin Statistics, 32 of 33
Inferential Statistics are used:
a.
b.
c.
d.
To describe whether a sample has more females or
males.
To reduce a data file to easily understood
summaries.
To make predictions about populations using
sample data.
To predict the sample data we will get when we
know the population.
Agresti/Franklin Statistics, 33 of 33