Stats
Tortor11111
StatisticsinSurveysandPollsPart1studentnotes.pptxStatistics in Surveys and Polls Part 1: Types of Surveys and Non-random Sampling Methods
1
1
Definitions
Surveys– an important kind of observational study; a sample is gathered from the population
Polls– a specific type of survey; usually by phone or mail; usually a political or social topic, interested in opinions and attitudes
2
2
Types of Surveys
Face-to-face surveys
Mail surveys
Telephone interview surveys
E-mail/Internet/Text surveys
3
3
Reminder
Opinions of all registered voters
Opinions of selected registered voters
Population of units = all registered voters
Unit = a registered voter
4
4
Types of sampling methods
Non-random sampling
Convenience sampling
Voluntary response sampling
Quota sampling
Snowball sampling
Random sampling
Simple random sampling
Systematic sampling
Stratified sampling
Cluster sampling
Multi-stage sampling
Also called non-probability sampling. Sampling in which units’ responses in population do not have same chance of being included in the sample.
Also called probability sampling. Sampling in which units’ responses in population do have same chance of being included in the sample.
5
5
Chapter 2: The Problem with Samples (Part 1)
Bad sampling techniques often produce sample information that does not reflect the population. These techniques introduce bias: “systematically favoring certain outcomes or responses”
Non-random sampling techniques
Convenience sampling
Voluntary response sampling
Quota sampling
Snowball sampling
6
6
Convenience Sampling
Asking the first 100 people you contact at a mall what they think about product X
Problems/Bias?
Asking the first 10% of students on class roll what they think about changing a test date
Problems/Bias?
Asking your friends what they think about text book costs
Problems/Bias?
7
7
Voluntary Response Samples
Dr. Phil http://www.drphil.com/ asked his audience to respond to the following question; “If you could start over, would you have children again?”
Problems/Bias
Bill O’Reilly http://www.billoreilly.com/ asked his audience to respond to the following question; “Do you think secular politicians want to destroy Christmas?”
Problems/Bias
A company provides ambulance service to a town. The town paper asked readers to call in with a yes/no vote on keeping the service
Problems/Bias
8
8
Quota Sampling
Used in market research
Population of units are divided into groups called strata
Strata consist of similar traits such as age, sex, states
Selection of units within strata is non-random
Units are selected so that the % of trait in sample is same as in the population
9
9
Quota Sampling Example
Suppose you want to survey 100 high school students from a particular school.
Strata = grade level
Of 1000 students at school, there are 150 eleventh graders.
______% of students are 11th graders
If you want to survey 100 students, how many of these students should be 11th graders?
10
10
Snowball Sampling
Initially, contact a few potential respondents and then ask them whether they know of anybody with the same characteristics that you are looking for in your research.
Examples
vegetarians / cyclists / people with a particular disability / people who support a particular political party, teachers etc.
Initial contacts may well have knowledge (through e.g. support group) of others.
11
11
yes
no
yes
no
yes
yes
no
no
yes
no
yes
no
no
yes
no
no
yes
yes
yes
no
yes
no
yes
no
yes
yes
no
no
yes
no
yes
no
no
yes
no
no
yes
yes
yes
no
no
yes
Population
yes
no
no
yes
no
yes
yes
no
no
yes
no
no
yes
yes
no
yes
no
yes
yes
no
no
yes
yes
no
yes
no
yes
yes
no
no
yes
yes
no
yes
no
yes
yes
no
no
yes
yes
no
no
yes
no
no
yes
yes
yes
no
no
yes
no
no
yes
no
no
yes
yes
yes
yes
no
yes
yes
no
no
yes
yes
no
no
yes no no yes no no yes yes yes
no
yes no no yes no no yes yes yes
yes
yes
no
no
yes
no
no
yes
yes
no
no
yes
Sample
no
yes
yes
no
no
yes
yes
yes
no
no
yes
no
no
yes
no
yes
yes
yes
yes
no
yes
yes
no
yes
yes
no
no
no
yes
yes
no
