sampling

The policy of inferring the behavior of a whole batch by studying a fraction of it. [MF essample, fr. L. exemplum, taking out]

- biological s. denotes s. that can be taken without jeopardy to the whole organism ( e.g., for hematological or biochemical study). Because of the complexity of biological samples it is usually supposed that the source of the sample is thoroughly mixed and hence representative; this assumption is often not true, e.g., in genetic studies in mosaic patients.

- chemical s. a sample that is obtained by whatever means is convenient and then purified of irrelevant elements before analysis; the assumption of thorough mixing is not necessary.

- continuous interleaved s. a strategy in speech processing for cochlear implants in which brief pulses are presented to each electrode in a nonoverlapping sequence.

- haphazard s. the assembly of data in an unprescribed and undefined fashion that allows no sound scientific inferences other than establishing the existence of types. (Finding even one unicorn in such a set would establish that unicorns can exist, but no inference about their prevalence could be made from it.) Cf.:random sample.

- random s. a selection of elements from a population such that each possible outcome is independent of other possible outcomes and the probability of each member of the population being chosen is equal.

- snowball s. a method whereby the names of prospective interview subjects for a statistical study are obtained from subjects already interviewed for the study.

* * *

sam·pling 'sam-pliŋ n

1) the act, process, or technique of selecting a suitable sample specif the act, process, or technique of selecting a representative part of a population for the purpose of determining parameters or characteristics of the whole population

2) SAMPLE <obtain a \sampling of urine>

* * *

sam·pling (samґpling) the selection or making of a sample.