2. SamplingProcess of choosing arepresentative portionof the entire population is called Sampling.
3. PopulationThe entire group ofpeople,events,or things ofinterest that the researcherwishes to investigate.Example:For example, you might beinterested in the laundrydetergent preferences ofPakistani women who livein urban areas. This groupof people is the populationwhose preferences you willstudy.
4. ElementAn element is a singlemember of the population.Example:If in an organization theresearcher wants to studythe profile data of workersin population , then eachworker is an element inthis population.
5. SampleA sample is a subset of thepopulation. It contains somemembers selected from it.Example:The Population of GCUFstudents is 600,only 200GCUF are included as thetarget population and only100 students are chosen assamples for the actual study.
6. Sampling UnitThe sampling unit is the element or set ofelements that is available for selection insome stage of sampling process.Example:In a Sampling Unit samples are cityblocks,households,and individuals within households.
7. SubjectA subject is a single memberof the sample.
8. Example of Sampling Elements
9. ParametersThe characteristics of the population.Such as the population mean, thethe population variance etc.
10. RepresentativenessWe calculate the sample statistics so thatthese can be used as estimates of thepopulation parameters.
11. Reasons for Sampling Sampling is used becauseSave time and moneyAccurate measurementWide surveyScientific researchReduce the demands on resources i.e. cost of investigationWhen results are quickly required
12. The Sampling Process
13. 1.Define the PopulationSampling Process begins with defining thetarget population. The population must bedefined in terms of elements, geographicalboundaries and time.Example:For an advertising agency interested inreading habits of elderly people, the targetpopulation might be the population aged 50and over.
14. 2. Determine the sample frame The sample frame is the list of all elements in the population from which the sample is drawn. Example:Telephone book directoryVoter listRandom digit dialing This is essential for probability sampling.
15. 3.Determine the SampledesignThere are two major types of sampling design:probability and non probability sampling.In probability sampling, the elements in thepopulation have some known, non-zerochance or probability of being selected assample subjects.In non probability sampling, the elements donot have a known or predetermined chance ofbeing selected as subjects.
16. 4.Determine the sample size Determining the sample size will be based on six factors such as:The research objective;Level of Accuracy desiredThe amount of variability in the population itself;Cost and time to generate sampleYour knowledge of the size of populationExperience with the risk of sampling
17. 5.Execute the sample processThe final step in the sample process involvesexecution of the operational sampling plan.It is important that this step include adequatechecking to make sure that specifiedprocedures are implemented.
18. Probability SamplingProbability sampling involvesthe selection of elements fromthe population using random inwhich each element of thepopulation has an equal andindependent chance of beingchosen.
19. Types of Probability SamplingSimple RandomSampling:In which every element in thepopulation has a known andequal chance of being selected as a subject.
20. Example:If a sample of 100 students is to be selectedfrom a population of 1000 students, then it isknow to every one that each student has1000/100 i.e. 1 chance in 10 being selected.
21. •Stratified Random Sampling Stratified random sampling involves dividing up the population into smaller groups, and randomly sampling from each group. Types:• Proportionate• Disproportionate
22. Example:Randomly select 1 to5 numbers as like4,7,13,19 and 21.Note, one element isselected from eachcolumn.
23. •Restricted/ComplexProbability Sampling As an alternative to the simple random sampling design, several complex probability sampling designs can be used. These probability sampling procedures offer a viable, and sometimes more efficient, alternative to the unrestricted design. The five most common complex…… next all probability sampling types under it.
24. •Systematic Sampling The systematic sampling design involves drawing every nth element in the population starting with a randomly chosen element between 1 and n.
25. Example There are 260 houses and a sample of 35households is desired. We have to sampleevery nth house starting from a randomnumber from 1 to 7.Let us say that the randomsample number was 7,then houses numbered7,14,21,28, and so on, would be sampled until35 houses were selected.
26. • Cluster Sampling Cluster samples are used when population is divided into groups or clusters.Then,a random sample of clusters is drawn and for each selected cluster either all the elements or a sample of elements are included in the sample.
27. Types Of Cluster SamplingSingle Stage Cluster SamplingMulti Stage Cluster Sampling And other specific type isArea Sampling
28. •Single Stage Sampling In which involves the division of the population into convenient clusters , randomly choosing required number of clusters as sample subjects, and investigating all the elements in each of the randomly chosen clusters.
29. • Multi Stage Sampling Involves choosing sample using more than two sampling techniques. This type is rarely used of the complexity of its application. Its requires a lot of effort,time,and cost.
30. •Area Sampling It is a method of cluster sampling and in connection With selection of sampling area with help of maps. Area sampling is less expensive than most other probability sampling designs. Example: The city of Karachi can be divided on the basis of municipal wards of zone. A random selection of this is made within each of the areas selected; a sub sample of locality or sample of residence is taken & then investigated.
31. Double SamplingThis plan is resorted to when further information isneeded from which some information has alreadybeen collected for the same study. A sampling designwhere initially a sample is used in a study to collectsome preliminary information of interest, later asubsample of this primary sample is used to examinethe matter in more detail, is calls double sampling.
32. Double SamplingSimple Definition: The same sample or a subset of the sample is studied twice is called Double Sampling.
33. Non Probability SamplingIn no probability sampling designs, theelements in the population do not haveany probabilities attached to their beingchosen as sample subject.
34. •Convenience SamplingConvenience sampling refers to the collection ofinformation from members of the population whoare conveniently available to provide it.It involves the non random selection of subjectswho are conveniently available.Example:A Pepsi contest was held in shopping mall visitedby many shoppers. Those inclined to take the testmight form the sample for the study of how manypeople prefer Pepsi over Coke or product X toproduct Y.Such sample is a Convenience sampling
35. Purposive Sampling This is necessarily useful when a group of subjects is needed to participate in a pretest of newly developed instruments or when a group of experts is desirable to validate research information. Types:• Judgment sampling• Quota sampling
36. •Judgment Sampling Judgment sampling involves the nonrandom selection of elements based on the researcher’s judgment and knowledge about the population.
37. Example: A TV researcher wants a quick sample of opinions about a political topic. He stops what seems like people in the street to get their views.
38. •Quota SamplingQuota sampling, a second type ofpurposive sampling, ensures thatcertain groups are adequatelyrepresented in the study throughthe assignment of a quota. Generally,the quota is fixed for each subgroupbased on the total numbers of eachgroup in the population.
39. Example:A sample of 40 students can be selected from a groupof 200 students comprising of 120 boys and 80 girls.to make the sample representative, the group of 40should include 24 boys and 16 girls (i.e. 120:80=3:2).
40. Table. Probability and nonprobability sampling designs