Statistics 528  Lecture 13
1
Statistics 528  Lecture 13
Prof. Kate Calder
1
Sampling Design
The idea of sampling:
We want to say something about a
population
 the entire group of
individuals that we want information about.
To get at this we take a
sample
 a part of the population that we actually
examine in order to gather information.
Statistics 528  Lecture 13
Prof. Kate Calder
2
Why take a sample?
It may be impossible to collect information about every member of the
population.
– Time
– Cost
– Convenience
The information from a sample is often adequate and easier to obtain.
Statistics 528  Lecture 13
Prof. Kate Calder
3
Example:
The Lantern wanted to know how Columbus residents rate the
movie “The Lord of the Rings: The Return of the King.” They asked
100 people coming out of the first showing of this movie at the AMC
Lennox theatre and noted their ratings.
Population: Columbus Residents
Sample: 100 people attending first show
Variable of interest: Rating of movie
Statistics 528  Lecture 13
Prof. Kate Calder
4
•
Since we make conclusions about a population based on the
information obtained from a sample, it is important that the units in the
sample are representative of the entire population
.
•
The
sampling design
, the method chosen to select the sample from the
overall population, has important consequences. Poor sampling
designs can yield misleading conclusions.
Statistics 528  Lecture 13
Prof. Kate Calder
5
•
A sampling method is
biased
if it systematically favors certain
outcomes.
•
Some commonly used but biased sampling designs are …
Statistics 528  Lecture 13
Prof. Kate Calder
6
1. Voluntary Response Survey
A
voluntary response sample
consists of people who choose
themselves by responding to a general appeal. Voluntary response
samples are biased because people with strong opinions, especially
negative ones, are most likely to respond.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentStatistics 528  Lecture 13
2
Statistics 528  Lecture 13
Prof. Kate Calder
7
Example:
•
The ABC news program Nightline once asked their viewers whether
the United Nations should continue to have its headquarters in the
United States. In order to have their opinions counted, viewers had to
call a 1900 number and pay a small fee. More than 186,000 callers
responded and
67%
said “No.”
•
A nationwide poll with a proper sampling design found that less than
28 %
of US adults want the UN to move out of the United States.
Statistics 528  Lecture 13
Prof. Kate Calder
8
2. Convenience Sampling
Convenience sampling
chooses the individuals easiest to reach to be
in the sample.
Examples:
This is the end of the preview.
Sign up
to
access the rest of the document.
 Winter '09
 Calder
 Statistics, Prof. Kate Calder

Click to edit the document details