Sampling Plans

Basic Sampling Concepts

• Population– The aggregate of cases in which a researcher is

interested• Sampling– Selection of a portion of the population (a sample) to

represent the entire population

• Eligibility criteria

– The characteristics that define the population

• Inclusion criteria

• Exclusion criteria

Basic Sampling Concepts (cont.)

• Strata– Subpopulations of a population (e.g., male/female)

• Target population– The entire population of interest

• Accessible population– The portion of the target population that is accessible

to the researcher, from which a sample is drawn

Sampling Goal in Quantitative Research

• Representative sample– A sample whose key characteristics closely

approximate those of the population—a sampling goal in quantitative research

• More easily achieved with:– Probability sampling– Homogeneous populations– Larger samples

Sampling Problems in Quantitative Research

• Sampling bias– The systematic over- or under-representation of

segments of the population on key variables when the sample is not representative

• Sampling error– Differences between sample values and population

values

Types of Sampling Designs

• Probability sampling

– Involves random selection of elements: each element has an equal, independent chance of being selected

• Nonprobability sampling

– Does not involve selection of elements at random

Question

Is the following statement True or False?• The difference between sample values and

population values is referred to as the sampling bias.

Answer• False– The sampling bias is the systematic over- or under-

representation of segments of the population on key variables when the sample is not representative. Sampling error is the difference between sample values and population values.

Types of Nonprobability Sampling—Quantitative Research

• Convenience sampling • Snowball (network) sampling • Quota sampling• Purposive sampling

Convenience Sampling

• Use of the most conveniently available people– Most widely used approach by quantitative

researchers– Most vulnerable to sampling biases

Snowball Sampling

• Referrals from other people already in a sample– Used to identify people with distinctive

characteristics – Used by both quantitative and qualitative

researchers

Quota Sampling

• Convenience sampling within specified strata of the population– Enhances representativeness of sample – Infrequently used, despite being a fairly easy

method of enhancing representativeness

QuestionWhich type of sampling is most vulnerable to bias?a. Convenience samplingb. Snowball samplingc. Quota samplingd. Purposive sampling

Answer

a. Convenience sampling• Although it is the most widely use approach for

quantitative researchers, convenience sampling is the most vulnerable to sampling biases. Snowball, quota, and purposive sampling are less subject to bias.

Consecutive Sampling

• Involves taking all of the people from an accessible population who meet the eligibility criteria over a specific time interval, or for a specified sample size– A strong nonprobability approach for “rolling

enrollment” type accessible populations – Risk of bias low unless there are seasonal or

temporal fluctuations

Purposive (Judgmental) Sampling

• Sample members are hand-picked by researcher to achieve certain goals– Used more often by qualitative than quantitative

researchers– Can be used in quantitative studies to select

experts or to achieve other goals

Types of Probability Sampling

• Simple random sampling• Stratified random sampling• Cluster (multistage) sampling• Systematic sampling

Simple Random Sampling

• Uses a sampling frame – a list of all population elements

• Involves random selection of elements from the sampling frame– Not to be confused with random assignment to

groups in experiments– Cumbersome; not used in large, national surveys

Stratified Random Sampling

• Population is first divided into strata, then random selection is done from the stratified sampling frames

• Enhances representativeness– Can sample proportionately or disproportionately

from the strata

Cluster (Multistage) Sampling

• Successive random sampling of units from larger to smaller units (e.g., states, then zip codes, then households)– Widely used in national surveys – Larger sampling error than in simple random

sampling, but more efficient

QuestionIs the following statement True or False?• Stratified random sampling is associated with a larger

sampling error but it is more efficient.

Answer• False– Stratified random sampling enhances

representativeness; cluster sampling is associated with a larger sampling error but is considered more efficient.

Sample Size

• The number of study participants in the final sample– Sample size adequacy is a key determinant of

sample quality in quantitative research. – Sample size needs can and should be estimated

through power analysis.

Sampling in Qualitative Research

• Selection of sample members guided by desire for information-rich sources

• “Representativeness” not a key issue• Random selection not considered productive

Methods of Sampling in Qualitative Research

• Convenience (volunteer) sampling• Snowball sampling• Purposive sampling• Theoretical sampling

Types of Purposive Sampling in Qualitative Research (Examples)

Maximum variation sampling Extreme/deviant case sampling Typical case sampling Criterion sampling Sampling confirming and disconfirming cases

Theoretical Sampling

Preferred sampling method in grounded theory research

Involves selecting sample members who best facilitate and contribute to development of the emerging theory

QuestionIs the following statement True or False?• Sampling in qualitative research is guided more by

the desire for rich sources of information than by the need for random selection.

Answer• True– Selection of sample members for qualitative

research is guided by the desire for information-rich sources. The representativeness of the sample is not a key aspect and random selection is not considered productive.

Sample Size in Qualitative Research

• No explicit, formal criteria• Sample size determined by informational needs• Decisions to stop sampling guided by data saturation• Data quality can affect sample size.

Sampling in the Main Qualitative Traditions

Ethnography Mingling with many members of the culture—a “big

net” approach Informal conversations with 25 to 50 informants Multiple interviews with smaller number of key

informants

Sampling in Phenomenology

Relies on very small samples (often 10 or fewer) Participants must have experienced phenomenon of

interest

Sampling in Grounded Theory

• Typically involves samples of 20 to 40 people • Selection of participants who can best contribute to

emerging theory (usually theoretical sampling)