Section 5.1
Designing Samples
Malboeuf 2009
Observational vs. Experiment
An observational study observes
individuals and measures variable of
interest but does not attempt to influence
the responses.
 An experiment, on the other hand,
deliberately imposes some treatment on
individuals in order to observe their
responses.

AP Statistics, Section 5.1, Part 1
3
Population and Sample
The entire group of individuals that we
want information about is called the
population.
 A sample is a part of the population that
we actually examine in order to gather
information.

AP Statistics, Section 5.1, Part 1
4
Sampling vs. a Census
Sampling involves studying a part in order
to gain information about the whole.
 A census attempts to contact every
individual in the entire population.

AP Statistics, Section 5.1, Part 1
5
How to capture a “Sample”
Getting a portion of the population is not
difficult.
 Getting a good sample is difficult.
 Creating a plan to do this is called “sample
design”.

AP Statistics, Section 5.1, Part 1
6
Voluntary response sample (example: Call
in opinion polls). Read “Call-in opinion
polls” (p272)
 The problem with call in opinion polls is
that the people who answer the polls tend
to have strong opinions, especially strong
negative opinions.
 This sample is biased; this sample is not
representative of the population.

AP Statistics, Section 5.1, Part 1
7
How not to sample cont.




Convenience sample (example: Mall intercept
interviews) Read “Interviewing at the mall”
(p272)
Convenience sampling may not get you access
to all the people in the population.
Interviewers often avoid people who may make
them feel uncomfortable.
This sample is biased; this sample is not
representative of the population.
AP Statistics, Section 5.1, Part 1
8
Bias

The design of a study is biased if it
systematically favors certain outcomes.
AP Statistics, Section 5.1, Part 1
9
Both voluntary response samples and convenience samples choose a sample that
is almost guaranteed not to represent the entire population. When choosing your
sample it is very important to try to avoid bias. Two additional types of sampling
bias are:
Non-Response Bias: when an individual chosen for the sample does not
participate. For example, does not return a mailed survey
Under-Coverage Bias: when some groups of the population are left out of the
process of choosing the sample. For example, not being able to get a list with all
the adults in the USA who are on a specific type of medication
Data can also be biased by factors that are not related to
the method by which a sample was chosen. Below are two
common factors that can result in bias.
Non Sampling Bias:
* The wording of a question
“Almost two thirds of the people in the USA would
like to see English as the only language used in
official documents. Are you in favor of this?”
How to sample
The best way to sample is to use a “simple
random sample”
 A simple random sample (SRS) of size n
consists of n individuals from the
population chosen in such a way that
every set of n individuals has an equal
chance to be the sample actually selected.

AP Statistics, Section 5.1, Part 1
12
How to create a SRS

Choose an SRS in two steps:
 Step
1: Label. Assign a numerical label to
every individual in the population.
 Step 2: Random Assignment.
Random number table (Table B)
 Random number generator (RandInt in the TI-83)

AP Statistics, Section 5.1, Part 1
13
AP Statistics, Section 5.1, Part 1
14
Stratified Random Sample

To select a stratified random sample,
first divide the population into groups of
similar individuals, called strata. Then
choose a separate SRS in each stratum
and combine these SRSs to form the full
sample.
AP Statistics, Section 5.1, Part 1
15
Multistage Sampling Design
Randomly choose stage 1 strata (for
example, states)
 Randomly choose stage 2 strata (for
example, cities within states)
 and so on until you get down to the
sample size.

AP Statistics, Section 5.1, Part 1
16
“Random” is the key

Good sampling technique uses random
selection to reduce the possibility of bias.
AP Statistics, Section 5.1, Part 1
17
Cautions about sample surveys
Undercoverage occurs when some
groups in the population are left out of the
process of choosing the sample.
 Nonresponse occurs when an individual
chosen for the sample can’t be contacted
or does not cooperate.

AP Statistics, Section 5.1, Part 1
18
Cautions about sample surveys

Response bias. Respondents may lie if
they feel uncomfortable telling the truth.
AP Statistics, Section 5.1, Part 1
19
Cautions about sample surveys

Wording of questions. “It is estimated
that disposable diapers account for less
than 2% of the trash in today’s landfills. In
contrast, beverage containers, third-class
mail and yard wastes are estimated to
account for about 21% of the trash in
landfills. Given this, in your opinion, would
it be fair to ban disposable diapers?”
AP Statistics, Section 5.1, Part 1
20
Why Sample?
We want to make inferences about the
population as a whole.
 We can’t afford to talk to everyone.
 Even though two samples, following the
same design most probably will give us
different results, those results are
reasonable estimates of the population as
a whole

AP Statistics, Section 5.1, Part 1
21
How to get the best estimates?

Large random sample give more precise
results than smaller sample.
AP Statistics, Section 5.1, Part 1
22
Assignment

Exercises: 5.1-9 all, 11-15 odd
AP Statistics, Section 5.1, Part 1
23