Chapter 14 - Sampling Flashcards
Population
Entire group the researcher wishes to investigate (i.e.,
target population)
Element
A single member of the population
Sample
Some elements (or a subset) of the population
Sampling unit
Elements available/considered for selection at a
particular stage of the sampling process
* Unit of observation (measurement) and unit of analysis
Subject
A single member of the sample
How do we obtain representative samples?
– Define the target population
– Determine the sample frame
– Determine the sampling design/method
* Probability vs. nonprobability sampling
– Determine the appropriate sample size
– Execute the sampling process
Probability sampling
Elements in the population have a known,
nonzero chance/probability of being selected
as sample subjects
Simple random sampling
Each element has known and equal probability of selection
Systematic sampling
Randomly select initial point, then every nth element
Stratified random sampling
– Strata: distinct and non-overlapping homogeneous subgroups
– Proportionate vs. disproportionate stratified sampling
Cluster sampling
– Clusters: “natural,” relatively heterogeneous subgroups
– A common type is area sampling
– Single-stage vs. multistage cluster sampling
Double sampling
– Select a subset of the initial sample for further research
Nonprobability sampling
– Elements in the population do not have a known or
predetermined chance of being selected as subjects
* Inclusion/exclusion of elements left to the discretion of the
researcher
– Cannot generalize findings to the target population
with any measured degree of confidence
* However, may still result in a reasonably “representative”
sample
– Particularly useful when researchers are more
concerned with obtaining preliminary information in a
quick and inexpensive way than with generalizability
Convenience sampling
Elements that are most readily available
Snowball (referral) sampling
Initial respondents identify other respondents
Judgment sampling
– Selecting elements for a specific purpose
– When a limited number or category of people has the
required information
Quota sampling
– A form of stratified sampling
– Population is divided into strata, but element selection is
made on a convenience basis
Exercise 14.1
A medical inspector wants to estimate the overall
average monthly occupancy rates of the cancer
wards in 80 different hospitals which are evenly
located in the northwestern, southeastern,
central, and southern suburbs of New York City.
Simple random sampling
or
Cluster sampling
The McArthur Co. produces special vacuum cleaners… About
a thousand of these are produced every month with stamped
serial numbers and stored serially in a stock room. Once a
month, an inspector does a quality control check on 50 of these. When he certifies them as to quality, the units are released from the stock room for sale. The production and sales managers, however, are not satisfied with the quality control check since, quite often, many of the units sold are returned by customers because of various types of defects. What would be the most useful sampling plan to test the 50 units?
Simple random sampling
or
Systematic sampling
A consultant had administered a questionnaire to
some 285 employees using a simple random
sampling procedure. As she looked at the
responses, she suspected that two questions
might not have been clear to the respondents.
She would like to know if her suspicion is wellfounded.
Double sampling
The executive board of a relatively small university
located in Europe wants to determine the attitude of
their students toward various aspects of the
university. … The university specializes in the social
sciences and humanities and has 5 faculties, 6 service
departments, 8 research centers, and 2 graduate
schools. The executive board has asked you to come
up with a sampling plan.
Stratified random sampling
An applied researcher at the Ontario Police College conducted
a job analysis of police managers in Ontario. The sampling
plan was designed to ensure representation from various ranks
(e.g., Sergeant to Chief), functions (e.g., Patrol, Criminal
Investigation, Administration), and service sizes. The
researcher requested certain types and numbers of respondents
from each service. Police services chose which of their
members would participate in the survey.
Quota sampling
A researcher wants to investigate the
relationship between employee engagement and
organizational citizenship behaviours. She calls
a former classmate who is now VP of a local
manufacturing company and asks him if she
could collect data from his firm’s employees.
Convenience sampling
* This is how most organizational research is
actually done!
Sample Size Determination
- Parameter precision
– Degree of confidence (e.g., 95%)
– Specified level of precision (i.e., confidence interval)
– Amount of variability
– Population size (if population is relatively small)
Sampling for qualitative studies
– Purposive (judgment) sampling
– Theoretical sampling
* Theoretical saturation
Sampling method AND sample size important to
establish sample representativeness…WHY?
– A large enough sample size is irrelevant if we fail to
use an appropriate sampling method
– No sampling method, however sophisticated, is useful
if the sample size is inadequate
Sampling
The process of selecting items from the population so that the sample characteristics can be generalized to the population. Sampling involves both design choice and sample size decisions.
Population
The entire group of people, events, or things that the researcher desires to investigate.
Element
A single member of the population.
Sample
A subset or subgroup of the population.
Sampling unit
The element or set of elements that is available for selection in some stage of the sampling process.
Unit of analysis
The level of aggregation of the data collected during data analysis.
Subject
A single member of the sample.
Sample size
The actual number of subjects chosen as a sample to represent the population characteristics.
Sampling frame
A (physical) representation of all the elements in the population from which the sample is drawn.
Probability sampling
The sampling design in which the elements of the population
have some known chance or probability of being selected as
sample subjects.
Nonprobability sampling
A sampling design in which the elements in the population do not have a known or predetermined chance of being selected as sample subjects.
Simple random sampling
A probability sampling design in which every single element in the population has a known and equal chance of being selected as a subject.
Complex probability sampling
Several probability sampling designs (such as systematic and
stratified random), which offer an alternative to the cumbersome, simple random sampling design.
Systematic sampling
A probability sampling design that involves choosing every nth element in the population for the sample.
Stratified random sampling
A probability sampling design that first divides the population
into meaningful, nonoverlapping subsets, and then randomly
chooses the subjects from each subset.
Proportionate stratified random sampling
A probability sampling design in which the number of sample
subjects drawn from each stratum is proportionate to the total number of elements in the respective strata.
Cluster sampling
A probability sampling design in which the sample comprises
groups or chunks of elements with intragroup heterogeneity and intergroup homogeneity.
Area sampling
Cluster sampling within a specified area or region; a probability sampling design.
Multistage cluster sampling
A probability sampling design that is a stratified sampling of
clusters.
Double sampling
A probability sampling design that involves the process of
collecting information from a set of subjects twice – such as using a sample to collect preliminary information, and later using a subsample of the primary sample for more information.
Nonprobability sampling
A sampling design in which the elements in the population do not have a known or predetermined chance of being selected as sample subjects.
Convenience sampling
A nonprobability sampling design in which information or data for the research are gathered from members of the population conveniently accessible to the researcher.
Purposive sampling
A nonprobability sampling design in which the required
information is gathered from special or specific targets or groups of people on some rational basis.
Judgment sampling
A purposive, nonprobability sampling design in which the sample subject is chosen on the basis of the individual’s ability to provide the type of special information needed by the researcher.
Quota sampling
A form of purposive sampling in which a predetermined
proportion of people from different subgroups is sampled.
Precision
The degree of closeness of the estimated sample characteristics to the population parameters, determined by the extent of the variability of the sampling distribution of the sample mean.
Confidence
The probability estimate of how much reliance can be placed on the findings; the usual accepted level of confidence in social science research is 95%.
Efficiency in sampling
Attained when the sampling design chosen either results in a cost reduction to the researcher or offers a greater degree of accuracy in terms of the sample size.
Grounded theory
A systematic set of procedures to develop an inductively derived theory from the data.