Sample

In statistics and quantitative research methodology, a sample is a set of data collected and/or
selected from a statistical population by a defined procedure. The elements of a sample are
known as sampling points, sampling units or observations.

Typically, the population is very large, so doing a census or complete enumeration of all values
in the population is impractical or impossible. The sample generally represents a subset of a
manageable size. Samples are collected and statistics are calculated from the samples so that
inferences or extrapolations can be made from the sample to the population.

The data sample can be taken from a population "without replacement" (no element can be
selected more than once in the same sample), in which case the sample is a subset of a
population, or "with replacement" (one element can appear multiple times in a sample), in
which case the sample is a multisubset.

sample types

A complete sample is a set of objects from a source population that includes all objects that
satisfy a well-defined set of selection criteria. For example, a complete sample of Australian
men taller than two meters would consist of a list of all Australian men taller than two meters.
However, it would not include German men, tall Australian women or people under two
meters tall. So compiling such a complete sample requires a complete list of the source
population, including data on height, gender, and nationality for each member of the source
population. In the case of human populations, such a complete list is unlikely to exist, as the
human population is in the billions. However, such complete samples are often available in
other disciplines, such as the pool of players in a major sports division, the birth dates of
members of parliament, or a complete limited-magnitude list of astronomical objects.

An unbiased (representative) sample is a set of objects chosen from a complete sample using a
selection process that does not depend on the properties of the objects. For example, an
unbiased sample of Australian men taller than two meters might consist of a randomly
sampled subset of 1% of Australian men taller than two meters. However, a subset chosen
from the electoral register may be biased as, for example, men under 18 will not be on the
electoral register. In an astronomical context, an unbiased sample may consist of a fraction of
a full sample for which data are available, provided that the availability of the data is not
biased by individual source properties.

The best way to avoid bias or non-representation is to select a random sample, also known as
a probability sample. A random sample is defined as a sample in which each individual
member of the population has a known, non-zero chance of being selected as part of the
sample. The various types of random samples include simple random samples, systematic
samples, stratified random samples, and cluster random samples.

A sample that is not random is called a non-random sample or a non-probability sample. Some
examples of non-random sampling include convenience sampling, judgmental sampling,
intentional sampling, quota sampling, snowball sampling, and squaring nodes in quasi-Monte
Carlo methods.

Probabilistic sampling

• Random sampling: It is the sample whose formation needed a procedure of selection of

elements or group of elements in a way that gives each element a probability of inclusion in
the sample that is calculable and different from zero.

• Simple Random Sampling: It is the one in which every possible sample of the same size has
the same chance of being selected from the population.

• Random sampling with replacement: It is the one in which the elements of the sample can be
repeated, being present more than once in the sample, even participating only once in the
population.

• Systematic or catastrophic sampling: Consists of a random element, for example, one name
every ten on a list, the tenth piece produced on a production line, etc. Its main advantage is its
simplicity and flexibility, being easier to instruct field workers.

• Stratified sampling: Consists of dividing or stratifying the population into a number of non-
overlapping subpopulations and then extracting a sample from each stratum. This type of
sampling is also used when different data collection methods are applied to different parts of
the population.

• Representative sample: It is the sample from which the analysis can offer valid conclusions
about