2 SamplingHow we select from an infinite number of observations we could possibly makeWhy do we sample?Size of the populationCost of obtaining elementsConvenience and accessibility of elementsSampling is the process of obtaining information from a subset (sample) of a larger group (population)The results for the sample are then used to make estimates of the larger groupFrom Chapter 7 in Babbie & Mouton (2001)
3 Characteristics of a Good Sample Good sampling design should:Relate to the objectives of the investigationBe practical and achievable;Be cost – effective in terms of equipment and labour;Provide estimates of population parameters that are truly representative and unbiased.Ideally, representative samples should be:Taken at random so that every member of the population of data has an equal chance of selection;Large enough to give sufficient precision;Unbiased by the sampling procedure or equipment.
4 Sampling Terminology Element The unit about which information is collectedTypically the elements are peopleBut look at the section on “unit of analysis” again: any of them could be elements (schools, universities, corporations, etc.)
5 Sampling Terminology Population All the potential study elements, as definedCareful specification of the populationSample PopulationAlmost impossible to guarantee that every element meeting your definition of “the population” has a chance to be selected into the sample.Thus the “study population” will be somewhat smaller than “the population”
6 Sampling Terminology Sampling Unit Typically the sampling units are the same as the elements and probably the units of analysis(We are not going to look into more complex sampling units)Sampling FrameThe actual list of sampling units (or elements).e.g. if you want to study “Students at the University of Cape Town”, there is a list of such sampling units (but there are a number of definition issues to be resolved here)SampleA subset of a population selected to estimate the behaviour or characteristics of the population.Research design - sampling
7 Sampling Designs Basically two sampling strategies available: Probability samplingNon-probability Sampling
8 Probability Sampling Random Stratified Random Systematic Cluster Each member of the population has a certain probability to be selected into the sampleTypes of Probability SamplingRandomStratified RandomSystematicCluster
9 Random SamplingPopulation members are selected directly from the sampling frameEqual probability of selection for every member (sample size/population size)400/10,000 = .04Use random number table or random number generator
10 Systematic SamplingOrder all units in the sampling frame based on some variable and number them from 1 to NChoose a random starting place from 1 to N and then sample every k units after that
11 Stratified SamplingThe chosen sample contains a number of distinct categories which are organized into segments, or strataequalizing "important" variablesyear in school, geographic area, product use, etc.Steps:Population is divided into mutually exclusive and exhaustive strata based on an appropriate population characteristic. (e.g. race, age, gender etc.)Simple random samples are then drawn from each stratum.
13 Stratified SamplingThe sample size is usually proportional to the relative size of the strata.Ensures that particular groups (e.g. males and females) within a population are adequately represented in the sampleHas a smaller sampling error than simple random sample since a source of variation is eliminated
14 Cluster SamplingThe Population is divided into mutually exclusive and exhaustive subgroups, or clusters, usually based on geography or time periodEach cluster should be representative of the population i.e. be heterogeneous.Means between clusters should be the same (homogeneous)Then a sample of the clusters is selected.then some randomly chosen units in the selected clusters are studied.
15 Cluster Samplingdivide population into clusters (usually along geographic boundaries)randomly sample clustersmeasure units within sampled clusters
16 Non-probability Sampling Members selected not according to logic of probability (or mathematical rules), but by other means (e.g. convenience, or access)Types of Non-Probability Samplingconvenience samplingjudgement samplingsnowball samplingquota sampling
17 Convenience Sampling Convenience Sampling A researcher's convenience forms the basis for selecting a sample.people in my classesMall interceptsPeople with some specific characteristic (e.g. bald)
18 Purposive SamplingSelect the sample on the basis of knowledge of the population: your own knowledge, or use expert judges to identify candidates to selectTypically used for very rare populations, such as deviant cases.
19 Snowball Sampling Typically used in qualitative research When members of a population are difficult to locate, for covert sub-populations, non-cooperative groupsRecruit one respondent, who identifies others, who identify others,….Primarily used for exploratory purposesResearch design - sampling
20 Quota Sampling A stratified convenience sampling strategy Begins with a table that describes the characteristics of the target populatione.g. the composition of postgraduate students at UCT in terms of faculty, race, and genderThen select on a convenience basis, postgraduate students in the same proportions regarding faculty, race, and gender than in the populationOf course, the quota frame (the proportions in the table) must be accurateAnd biases may be introduced when selecting elements to studyResearch design - sampling