2 Sampling Terminology Sample Population or universe Population element A subset, or some part, of a larger populationPopulation or universeAny complete group of entities that share some common set of characteristicsPopulation elementAn individual member of a populationCensusAn investigation of ALL the individual elements that make up a population
3 Why Sample?SamplingCuts costsReduces labor requirementsGathers vital information quicklyMost properly selected samples give sufficiently accurate results
5 Target Population A.k.a., the Relevant population Operationally define All women still capable of bearing children vs.All women between the ages of 12 and 50Comic book reader?Does this include children under 6 years of age who do not actually read the words?
6 A list of elements from which the sample may be drawn Sampling FrameA list of elements from which the sample may be drawnA.K.A., the working populationMailing lists - data base marketersSampling services or list brokers
7 Two Major Categories of Sampling Probability samplingKnown, nonzero, & equal probability of selection for every population elementNonprobability samplingProbability of selecting any particular member is unknown
9 Convenience Sampling Also called haphazard or accidental sampling The sampling procedure of obtaining the people or units that are most conveniently available
10 Judgment Sampling Also called purposive sampling An experienced individual selects the sample based on his or her judgment about some appropriate characteristics required of the sample member
11 Quota SamplingEnsures that the various subgroups in a population are represented on pertinent sample characteristics to the exact extent that the investigators desireIt should not be confused with stratified sampling.
12 Snowball Sampling A variety of procedures Initial respondents are selected by probability methodsAdditional respondents are obtained from information (or referrals) provided by the initial respondents
13 Comparing the Nonprobability Techniques StrengthsWeaknessesConvenience SamplingLeast expensiveLeast time neededMost convenientSelection biasNot representativeJudgmental SamplingLow expenseLittle time neededConvenientSubjectiveDoes not allow generalizationsQuota SamplingCan control sample characteristicsMost likely not representativeSnowball SamplingCan estimate rare characteristicsTime consuming
14 Figure 12.8 Probability Sampling Techniques Most Commonly-UsedProbability Sampling TechniquesFigure Probability Sampling TechniquesProbability Sampling TechniquesSimple RandomSamplingSystematicSamplingStratifiedSampling
15 Simple Random Sampling A sampling procedure that ensures that each element in the population will have an equal chance of being included in the sample
16 Systematic Sampling A simple process Every nth name from the list will be drawnPeriodicityProblem that occurs in systematic sampling when the original list has a systematic pattern (I.e., the original list is not random in character)
17 Stratified Sampling Probability sample Subsamples are drawn within different strata using simple random samplingEach stratum is more or less equal on some characteristicDo not confuse with quota sample
18 Comparing the Probability Techniques StrengthsWeaknessesSimple Random SamplingEasily understoodCan project resultsExpensiveDifficult to construct sampling frameNo assurance of representativenessSystematic SamplingEasier to implement than SRSIncreased representativenessSampling frame not necessaryCan decrease representativenessStratified SamplingPrecisionIncludes all important subpopulationsSelection of stratification variables difficult
19 What is the Appropriate Sample Design? Degree of accuracyResourcesTimeAdvanced knowledge of the populationNational versus localNeed for statistical analysis
20 Choosing Between Nonprobability & Probability Sampling FactorNonprobabilityProbabilityNature of ResearchExploratoryConclusiveRelative Magnitude of Sampling & Nonsampling ErrorsNonsampling errors largerSampling errors largerPopulation VariabilityHomogeneous(low variability)Heterogeneous(high variability)Statistical ConsiderationsUnfavorableFavorableOperational Considerations
21 Internet SamplesRecruited Ad Hoc SamplesOpt-in Lists
22 Information Needed to Determine Sample Size Variance (standard deviation)Get from pilot study or rule of thumb (managerial judgment)Magnitude of errorManagerial judgment or calculationConfidence levelManagerial judgment
23 Sample Size Formula for Questions Involving Means
24 Sample Size Formula - Example Suppose a survey researcher is studying expenditures on lipstickWishes to have a 95 percent confident level (Z) andRange of error (E) of less than $2.00.The estimate of the standard deviation is $29.00.
30 E pq z n = Where: n = Number of items in samples 2Epqzn=Where:n = Number of items in samplesZ2 = The square of the confidence interval in standard error units.p = Estimated proportion of successq = (1-p) or estimated the proportion of failuresE2 = The square of the maximum allowance for error between thetrue proportion and sample proportion or zsp squared.
31 Sample Size for a Proportion: Example A researcher believes that a simple random sample will show that 60 percent of a population (p = .6) recognizes the name of an automobile dealership.Note that 40% of the population would not recognize the dealership’s name (q = .4)The researcher wants to estimate with 95% confidence (Z = 1.96) that the allowance for sampling error is not greater than 3.5 percentage points (E = 0.035)
32 Calculating Sample Size at the 95% Confidence Level 753=001225.922)24)(.84163(035( .46(.961.nqp2