sampling the world of probability and nonprobability sampling. © pine forge press, an imprint of...

Sampling

The world of probability and nonprobability sampling.

© Pine Forge Press, an imprint of Sage Publications, 2004

Sampling Methods

• Sampling methods are the procedures that primarily determine the generalizablity of research findings.

POPULATION

• Population: The entire set of individuals or other entities to which study findings are to be generalized

• The aggregation of elements that we actually sample from, NOT some larger aggregation that we wish we could have studied

• In cases where population is not bounded by geography or membership, a clear conceptual definition must be specified

Sampling Frame

• Sampling Frame: A list of all elements or other units containing the elements in a population

SAMPLE

• Sample: A subset of a population used to study the population as a whole

• N-1 or less of population.

ELEMENTS

• Elements: The individual members of the population whose characteristics are measured (and therefore, constitute the sample

Sampling methods that allow us to know in advance how likely it is that any element of a population will be selected for the sample & THAT EVERY ELEMENT

HAS SOME KNOWN CHANCE OF BEING SELECTED are termed probability sampling

methods.


Probability Sampling Methods

Non-Probability Samples

• Samples wherein the odds (chances) of each element being selected are

not known are called NON PROBAILITY SAMPLES.

Probability VS non-Probability

• With probability samples we can know the odds of being wrong in generalizing about no relationship in the population on the basis of a single sample score and we can make the odds of being wrong damn small!!!

• We compare our sample score to those obtained from a no relationship population if we had taken samples of the same size an infinite # of times. [Sampling distribution]

• With non probability sampling we have no idea about the representativeness of the sample We have no idea about our odds of being incorrect in generalizing to the population

Simple Random Sampling

Simple random sampling identifies cases strictly on the basis of chance.

As you know, flipping a coin and rolling a die both can be used to identify cases strictly on the basis of chance, but these procedures are not very efficient tools for drawing a sample.


Note on SRS

• Every element and every combination of elements has an equal chance of being included.

Simple Random Sampling

• Pros:• Almost Easiest• Requires little

knowledge of pop

• Cons:• Possibly larger

sampling error [more variation] from sample to sample

• Need to have a listing of population elements in some form

Systematic Random Sampling

The first element is selected randomly from a list or from sequential files, and then every nth element is selected.

In almost all sampling situations, systematic random sampling yields what is essentially a simple random sample. The exception is a situation in which the sequence of elements is affected by periodicity—that is, the sequence varies in some regular, periodic pattern.

For example, the houses in a new development with the same number of houses on each block (eight, for example) may be listed by block, starting with the house in the northwest corner of each block and continuing clockwise. © Pine Forge Press, an imprint of Sage Publications, 2004

If the sampling interval is 8 for a study in this neighborhood,every element of the sample will be a house on the northwestcorner—and thus the sample will be biased.


Systematic Random Sampling

• Pros• Easiest

• Cons• Possible periodicity• Need a list or

mapping of population

Cluster Sampling

Cluster sampling is useful when a sampling frame—a definite list—of elements is not available, as often is the case for [or when] large populations spread out across a wide geographic area or among many different organizations.

A cluster is a naturally occurring, mixed aggregate of elements of the population, with each element (person, for instance) appearing in one and only one cluster. Schools could serve as clusters for sampling students, city blocks could serve as clusters for sampling residents, counties could serve as clusters for sampling the general population, and restaurants could serve as clusters for sampling waiters.


Cluster Sampling is at least a two-stage procedure.

First, the researcher draws a random sample of clusters. (A list of clusters should be much easier to obtain than a list of all the individuals in each cluster in the population.)

Next, the researcher draws a random sample of elements within each selected cluster. Because only a fraction of the total clusters are involved, obtaining the sampling frame at this stage should be much easier.


Cluster samples often involve multiple stages, with clusters within clusters, as when a national study of middle school students might involve first sampling states, then counties, then schools, and finally students within each selected school .

Cluster Sampling

• Pros• Saves time• Saves money• Should allow for

closer supervision in the field

• Requires enumerating only part of the population

• Cons• Larger sampling

error [variation in score form sample to sample]

• Typically “requires” larger sample

Stratified random sampling ensures that various groups will be included.

First, all elements in the population (that is, in the sampling frame) are distinguished according to their value on some relevant characteristic (army rank, for instance: generals, captains, privates, etc.). That characteristic forms the sampling strata.

Stratified Random Sample

Next, elements are sampled randomly from within these strata: so many generals, so many captains, etc. Of course, in order to use this method more information is required prior to sampling than is the case with simple random sampling. Each element must belong to one and only one stratum.


Notes on SRS

• Strata are “layers,” levels, or groups• Often we want to make sure that we

include different types of people or people of different categories

• Often these categories are demographic like sex, race, social status

• When some of the categories are small, we may not sample enough from the category to analyze folks adequately

example

• Actual size:• White males 70%• White females 18%• Black males 2%• Black females 10%

• Sample ns & proportions:

• White males 100 (25%)

• White females 100 (25%)

• Black males 100 (25%)

• Black females 100 (25%)

Stratified Random Sample

• Pros:• Less sampling

error [variability from sample to sample]

• Able to analyze more about groups with small proportions in the population

• Cons:• For each element

need to have list of characteristics on which you want to stratify

• Hence may cost more and not be worth it…just tqake a larger SRS

Sometimes, a probability sample is not feasible or generalizability is not a possible.

Nonprobability sampling methods are often used in qualitative research; they also are

used in quantitative studies when researchers are unable to use probability selection methods.


• With non probability sampling we have no idea about the representativeness of the sample We have no idea about our odds of being incorrect in generalizing to the population

Availability Sampling

Elements are selected for availability sampling because they’re available or easy to find.

Thus this sampling method is also known as a haphazard, accidental, or convenience sample.

•Magazine surveys•Observing conversations in an on-line chat room

•Interviewing people on a street corner or at the mall•Surveying students in a classroom

Examples:


Availability Sampling

• Pros• Easiest

• Cons• Least information

Quota Sampling

Quota sampling is intended to overcome the most obvious flaw of availability sampling—that the sample will just consist of whoever or whatever is available, without any concern for

its similarity to the population of interest.

The distinguishing feature of a quota sample is that quotas are set to ensure that the sample represents certain characteristics in proportion to their prevalence in the

population.


Quota Sampling

• Pros• Although don’t

know “odds…” experience shows it’s typically “pretty good”

• Cons• Take more effort

than many• Need trustworthy

poll takers

Quota Sampling, continued…The problem is that even when we know that a quota sample

is representative of the particular characteristics for which quotas have been set, we have no way of knowing if the

sample is representative in terms of any other characteristics.

In Exhibit 5.9, for example, quotas have been set for gender only. Under the circumstances, it’s no surprise that the sample is representative of the population only in terms of gender, not in terms of race. Interviewers are only human;.


Note:

• Apparently, many reputable national polls use quota sampling and have been doing quite well.

Purposive Sampling

In purposive sampling, each sample element is selected for a purpose, usually because of the unique position of the

sample elements.

Purposive sampling may involve studying the entire population of some limited group (directors of shelters for homeless

adults) or a sub-set of a population (mid-level managers with a reputation for efficiency).

Or a purposive sample may be a “key informant survey,” which targets individuals who are particularly knowledgeable about

the issues under investigation.© Pine Forge Press, an imprint of Sage Publications, 2004

Purposive Sampling

• Pros• Often suffices…

snot rag analogy

• Cons

Snowball Sampling

Snowball sampling is useful for hard-to-reach or hard-to-identify populations for which there is no sampling frame, but the members of which are

somewhat interconnected (at least some members of the population know each other).

It can be used to sample members of such groups as drug dealers, prostitutes, practicing criminals, participants in Alcoholics Anonymous groups, gang leaders, informal

organizational leaders, and homeless persons.


More Snowball Sampling…More systematic versions of snowball sampling can reduce the potential for bias. For example, “respondent-driven sampling”

gives financial incentives to respondents to recruit peers


Snowball Sampling

• Pros• May be able to find

difficult to locate groups

• Cons• May run into a

“vein” or network which isn’t at all representative of such kinds of people

Ultimately, one of the determinants of sample quality is sample size.

Samples will be more representative of the population if they are relatively large

and selected through…

Probability Sampling Methods


Imagine that you plan to draw a sample of 500 from an ethnically diverse neighborhood.

But if you created sampling strata based on race and ethnicity, you could randomly select cases from each stratum, in exactly the same proportions.

The neighborhood population is 15% black, 10% Hispanic, 5% Asian, and 70% white.

If you drew a simple random sample, you might end up with somewhat disproportionate numbers of each group.

This is termed proportionate stratified sampling and it eliminates any possibility of sampling error in the sample’s distribution of ethnicity.


In Disproportionate Stratified Sampling, the proportion of each stratum that is included in the sample is intentionally varied from what it is in the population. In the case of the sample stratified by ethnicity, you might select equal numbers of cases from each racial or ethnic group:

•125 blacks (25% of the sample)

•125 Hispanics (25%)

•125 Asians (25%), and

•125 whites (25%).

In this type of sample, the probability of selection of every case is known but unequal between strata.


sampling the world of probability and nonprobability sampling. © pine forge press, an imprint of...

Documents