Send the link below via email or IMCopy
Present to your audienceStart remote presentation
- Invited audience members will follow you as you navigate and present
- People invited to a presentation do not need a Prezi account
- This link expires 10 minutes after you close the presentation
- A maximum of 30 users can follow your presentation
- Learn more about this feature in our knowledge base article
Sampling Designs and Sampling Procedures
Transcript of Sampling Designs and Sampling Procedures
Sampling Designs and Sampling Procedures
Rudi Gens, Catherine Gilmore, Brandon Moore, Andrew Seward, Venus Sung
1. Imagine that an agency or business has asked for help in gathering data about the number of sport anglers who fish off the coast of Georgia. What advice would you give about sampling? What method or combination of methods would generate the best results?
An investigation of all the individual
elements that make up a population.
Any complete group of entities
that share some common set
A subset, or some part,
of a larger population.
An individual member of a population.
1. Pragmatic reasons
> cuts costs
> reduces labor
> gathers vital information quickly
2. Accurate and reliable results
> if census is too big, more room for error
> fieldwork and data collection
more easily supervised
3. Destruction of test units
> can't use everything as a sample-
nothing will remain and/or tainted
for research study
What is the simplest
Equal probability for each member
Study of differences in career goals between freshmen, sophomores, juniors and seniors
Test your knowledge
Survey of professor about drinking behavior among college students
Interview of undocumented immigrants from Mexico
Sample of opinions about political announcement
Each element of sample randomly chosen
Each element in the population will have an equal chance of being included
Simplest technique, requires minimum advance knowledge of population
May not be feasible for larger populations
Simple Random Sampling
First selection of elements at random, then selecting every nth element from the list
Much more efficient than simple random sampling
Only applicable when population is logically homogenous
Dividing members of the population into homogeneous subgroups (strata)
Sampling most representative of a population
Not useful when the population cannot be exhaustively partitioned into disjoint subgroups
Sample economically while retaining the characteristics of a probability sample
Primary sampling unit is no longer the individual element in the population but a larger cluster of elements located in proximity to one another
Area sample is the most popular type of cluster sample (Oregon representing US)
Multistage Area Sampling
Be Accurate! Carefully define population so the proper sources are used from which you collect your data.
Identify Target Population
Sampling frame: list of elements from which a sample may be drawn (aka working population)
Select Sampling Frame
A single element or group of elements subject to selection in the sample
Occurs because of chance variation in the scientific selection of sampling units. Even if the sampling units are properly selected they are not likely to perfectly represent the population.
Random Sampling Error
Result from primarily the study of design and execution.
Systematic Sampling Error
What is the Appropriate Sample Design?
How accurate do you need to be?
Increased accuracy may require more resources
Degree of Accuracy
Resources-What are your limitations?
Some surveys take longer than others
Internet Sampling is Unique
Quick response times
Frequent users may be more selective
Lack of accessibility/ownership
Yields high response rates
Panel member might receive compensation
Eliminates lengthy recruitment process
Researchers can select panelists based on previous information
Random selection is a useful technique
Sampling frame of email addresses
Collection methods include customer lists, advertising banners, online sweepstakes, registration forms, mail, telephone
Recruited Ad Hoc Samples
Opt in: to give permission to receive selected email, such as questionnaires, from a company with an internet presence
Unsolicited e-mail can be viewed as spam
Can lead to closure of the survey site
Case Study 16.1
2. What other criteria besides accuracy would you expect to consider? What sampling methods could help you meet those criteria?
Of the following, who does NOT provide
Exhibit 16.1 (page 388)
Stages in the Selection of a Sample
"The Saltwater Information Program (SIP) permit is part of a nationwide effort to collect contact information annually for everyone who fishes recreationally in saltwater. Doing so will help state and federal fishing effort surveyors improve their ability to contact anglers periodically and ask them questions about their fishing activities. This information is the backbone of good saltwater fishery management.
Having an accurate Georgia “phone book” of all recreational saltwater anglers will provide a better picture of how many people go fishing and what they catch. This will result in a better understanding of the impact of recreational fishing on fish populations, and will lead to better fishery management decisions to create and maintain sustainable saltwater fisheries. It will also allow us to document the importance of saltwater recreational fishing so that services like boat ramps and fishing piers are provided and maintained."
Advanced knowledge of the population
National vs. Local
Lists may not be available
Preliminary study may be necessary
Limitations in developing countries
Design based on geographic proximity
Highly distributed population elements can be costly
A. Health insurance companies
B. Adoption agencies
D. Air conditioning contracting and systems
F. None of the above
The FREE, annual SIP permit is mandatory since January 1, 2013, for anyone who wants fish in saltwater.
As far as sampling techniques go, there is nothing random about it. This is mandatory selection, so non-probabilistic to start with. I would put it down as quota sampling.
Start by making a profile of the proposed target population including age, gender, ethnicity, educational status, economic status, and personal risk factors
Then record community wide factors and conditions
Sampling services and reverse directories
Sampling frame error: an error that occurs when certain sample elements are not listed or are not accurately represented in a sampling frame.
Primary, secondary, and tertiary sampling units
As sample size increases, random sampling error decreases.
Not due to chance unlike random sampling error.
Example: Highly educated respondents are more likely to cooperate with mail surveys than poor educated ones. Can you think of reasons why?