Cluster Sampling - Social Research Methods - Lecture Slides, Slides of Sociology

Download Cluster Sampling - Social Research Methods - Lecture Slides and more Slides Sociology in PDF only on Docsity!

Cluster sampling.

Non-Probability Sampling

 Cluster sampling  Haphazard sampling  Purposive sampling  Quota sampling  Snowball sampling  Heterogeneity sampling

Definitions

• Population
• Sampling frame
• Sample
• Subsample

Definition

• Cluster sampling is a sampling technique where the entire population is divided into groups, or clusters, and a random sample of these clusters is selected
• All observations in the selected clusters are included in the sample

Example

• Let's say that we have to do a survey of town governments in New York State
• Imagine taking a simple random sample of all the town governments of New York State in order to conduct personal interviews

Cluster Sampling

What might happen

• By the luck of the draw you will wind up with respondents who come from all over the state
• Your interviewers are going to have a lot of traveling to do
• It is for precisely this problem that cluster or area random sampling was invented

New York State

How is cluster sampling done?

• The population is divided into N groups, called clusters.
• The researcher randomly selects n clusters to include in the sample.
• The number of observations within each cluster Mi is known, and M = M 1 + M 2 + M 3 + ...
  • MN-1 + MN.
• Each element of the population can be assigned to one, and only one, cluster

What do we do?

• We decide to do a cluster sampling of five counties (cluster1=county; cluster 2=towns)
• Once these are selected, we go to every selected town government
• Clearly this strategy will help us to economize on our mileage
• Note: if we conduct phone/mail survey we might not worry about using this approach

When to Use Cluster Sampling?

1. Constructing a complete list of population elements is difficult, costly, or impossible.
2. Population is geographically spread
3. The population is concentrated in "natural" clusters (city blocks, schools, hospitals, etc.).

Example 1

• Imagine interviewing customers of a chain of hardware stores
• It may not be possible to list all of the of customers
• However, it would be possible to randomly select a subset of stores (stage 1 of cluster sampling) and then interview a random sample of customers who visit those stores (stage 2 of cluster sampling)

Example 2

• To conduct personal interviews of operating room nurses, it might make sense to randomly select a sample of hospitals (stage 1 of cluster sampling) and then interview all of the operating room nurses at each selected hospital (stage 2 of cluster sampling)

Example 3

• If we want to study drivers of Washington-Oregon highway, it will be impossible to construct a sample frame of all drivers at some point in time.
• Solution: We can design clusters of some road locations, randomly select these locations, and then within these locations sample the drivers

City Block

• A city block is the smallest area that is surrounded by streets
• City blocks are the space for buildings within the street pattern of a city
• City blocks are usually built-up to varying degrees and thus form the physical containers or ‘streetwalls' of public space

Nonprobability Sampling

• Qualitative researchers are more likely to use non- probability sampling since it allows the investigator to collect information from whomever is present in the setting
• A table of random numbers is not used, so cases are selected using non-probability procedures.

Copyright @ Allyn & Bacon 2003 Docsity.com

Types of Nonprobability Samples

• Haphazard sample - cases gotten in any manner
• Purposive sample uses as many possible cases that fit a particular criteria as can be gotten, with various methods.
• Quota samples are designed to get a certain proportions of cases (i.e.: 51% women, 49% women based on their proportion in the population). It is the proportion that matters, not the process of selection.
• Snowball sample gets cases using referrals from prior cases
• Heterogeneity sample gets broad spectrum of ideas or people

Copyright @ Allyn & Bacon 2003 Docsity.com

Accidental, Haphazard or Convenience Sampling

• Traditional “person on the street“ (Interviews conducted frequently by television news programs)

Accidental, Haphazard or Convenience Sampling

• Typical use of college students in psychological research is primarily a matter of convenience.

Accidental, Haphazard or Convenience Sampling

• In many research contexts, we sample simply by asking for volunteers

Disadvantage

• The problem with non-probability samples is that we have no evidence that they are representative of the populations we're interested in generalizing to -- and in many cases we would clearly suspect that they are not

Purposive sampling

• We sample with a purpose in mind
• We have one specific predefined group we are seeking (e.g., elderly; disabled; drug users, etc)

Types of purposive sampling

• Snowball sampling
• Quota sampling
• Heterogeneity sampling
• Haphazard sampling

Snowball sampling

• Snowball sampling
  • Appropriate when members of a population are difficult to locate