Sampling Strategies

1
Sampling Strategies
2
Definitions

• Population is the entire set of individuals or
  other entities to which study findings are to be
  generalized.
• Target population is a set of elements that was
  sampled or and to which the researcher would like
  to generalize study findings.
• Census is the study of the entire population.
• Sample is a subset of a population.
• Representative sample is a sample that looks
  like the population from which it was selected
  in all respects that are potentially relevant to
  the study. The distribution of characteristics
  among the elements of a representative sample is
  the same as the distribution of those
  characteristics among the total population. In
  unrepresentative sample, some characteristics are
  overrepresented or underrepresented.

3
Definitions

• Sampling frame is a list of all elements or other
  units containing the elements in a population.
• Sampling units are units listed at each stage of
  a multistage sampling design.
• Sampling error is any difference between
  characteristics of a sample and the
  characteristics of the population from which it
  was drawn. The larger the sampling error, the
  less representative the sample.

4
Two sampling research strategies

• Probability Sampling Strategies
• Non-Probability Sampling Strategies

5
1. Probability Sampling Strategies (Random or
Statistical Samples)

• Probability sample is one in which the units of
  analysis have been selected from the sampling
  frame (or sometimes directly from the population)
  by the process involving the use of random
  numbers.
• Random sampling is structured so that all unites
  within a population (or subset of the population)
  have equal probability of being selected.

6
The main advantage of random sampling is

• that it precludes any possibility of the
  researcher or evaluator consciously or
  unconsciously drawing a biased sample.

7
Probability sampling methods

• Simple random sample Each unit in the population
  has or is given a unique number, and then the
  sample is drawn according to random numbers
• Systematic random (random interval) sampling The
  first element is selected randomly, and then
  every nth element is selected from the list.
  Usually the interval between names on the list is
  determined by dividing the number of persons
  desired in the sample into the full population.

8
Probability sampling methods

• Stratified random sampling The population is
  divided into two or more strata (subpopulations)
  and a random sample is drawn from each strata
• Random cluster sample When it would be very
  expensive to collect data with a simple random
  sample (usually because of wide geographic
  dispersion), a random sample is drawn from
  naturally occurring clusters of the units of
  analysis (e.g. States, counties, cities,
  districts, schools, or households)

9
2. Non- Probability Sampling Strategies
(Non-Random Sampling)

• The social sciences often examine research
  situations where one cannot select the kinds of
  probability samples used in large-scale surveys,
  and which conform to the restricted needs of a
  probability sample. In these situations,
  investigators rely upon no probability samples.

10
Non-Propoability sampling methods

• Convenience Samples The convenience sample is
  sometimes referred to as an accidental, haphazard
  or availability sample. This category of sample
  relies on available subjectsthose who are close
  at hand or easily accessible.
• Purposive Sampling This category of sampling is
  sometimes called judgmental sampling. When
  developing a purposive sample, researchers use
  their special knowledge or expertise about some
  group to select subjects who represent this
  population. In some instances, purposive samples
  are selected after field investigations on some
  group, in order to ensure that certain types of
  individuals or persons displaying certain
  attributes are included in the study.

11
Non-Propoability sampling methods

• Snowball Sampling The basic strategy of
  snowballing involves first identifying several
  people with relevant characteristics and
  interviewing them or having them answer a
  questionnaire. These subjects are then asked for
  the names of other people who possess the same
  attributes as they do.
• Quota Samples A quota sample begins with a kind
  of matrix or table that creates cells or stratum.
  The quota sampling strategy then uses a
  nonprobability method to fill these cells. Units
  are selected proportionally from given strata of
  interests.