Research methodology for business four-2.pptx
- 2. Introduction •What is sampling? • Is the process involving the selection of a finite number of elements from a given population of interest, for purposes of inquiry/investigation. • Purpose of sampling is to gain information about the population by using samples. •What is a sample? • It is not possible to study the entire population. A decision is made based on only small fraction of a population. • Is a subset or some part of a larger population • Sample should possess all the characteristics of the population 24/07/2024 2
- 3. Cont. • To achieve reliable and valid information from a sample, the f/f should be considered • The sample size • the representativeness of the sample • Accessibility. • What is a sample design? • It is a definite plan for obtaining a sample from a given population • It refers to the technique or procedure the researcher would adopt in selecting items for the sample. • The sampling technique that we use should be • precise and easier to apply than others • reliable and appropriate for his research study. 24/07/2024 3
- 4. Sample size, sampling frame and sampling unit • A sampling frame is also known as source list – from which sample is to be drawn. • It is the list of possible sampling units from which the sample can be selected. • E.g. the names or ID no. of all students • Sample size (n) refers to the number of items to be selected from the universe to constitute a sample. • E.g. No. of students to be selected • A sampling unit is the ultimate unit/ elements of the population to be sampled. • It is that element or set of elements considered for selection in some stage of sampling. • A unit that is selected for study 24/07/2024 4
- 5. Reasons for Sampling Common reasons for sampling are: •Resource Limitations • A census can be extremely expensive and time-consuming. • Sampling can provide satisfactory results more quickly and at much lower cost. • Efficiency is the commonly known advantage of sampling •The physical impossibility of checking all items in the population • Conducting a census is not always feasible and possible. • Sampling is also the only process possible if the population is infinite or constantly in a state of movement to obtain the desired information about the population 24/07/2024 5
- 6. For this reason, sometimes census is impossible to check all items in the population. •Superior quality of results or Accuracy •Sample surveys are often more accurate than would be the case for a total census. •Sampling enable more accurate measurement for a sample study because it is conducted by trained and experienced investigators. 24/07/2024 6
- 7. Cont. • Sample surveys are more accurate than census for the following reasons: • Census requires • a very large staff/ Logistical problems:- everyone in sight is employed and this decrease the quality of interviews and lowering the rate of completions • lengthy interviewing period/ Problem of timeframe: impossible to specify a time of the study • Greater managerial requirement: involves greater supervision, record keeping, training, etc. • Generally, Interviewer mistakes, tabulation errors, and other non- sampling errors may increase during a census because of the increased volume of work. 24/07/2024 7
- 8. Cont. •Destructive nature of some tests •To test the quality of some products or items it may be necessary to consume it or destroy it. •Sampling remains the only choice when a test involves the destruction of the items under study. •Example: testing the quality of a commodity (beer, cigarette, coffee, etc.) 24/07/2024 8
- 9. Steps in Sampling Design •Identifying the population •Secure a sampling Frame •Determining the method of sampling •Identifying parameters of interest •Determining the Sample Size •Budgetary constraints •Sampling procedure 24/07/2024 9
- 10. Criteria of selecting a sampling procedure •Degree of accuracy • The degree of accuracy required or the researcher’s tolerance for sampling and non-sampling error may vary from project to project, • Cost savings or another benefit may be a trade-off for a reduction in accuracy. • Exploratory research project, a high priority may not be placed on accuracy because a highly representative sample may not be necessary. • Conclusive projects, the sample result must precisely represent a population’s characteristics, and the researcher must be willing to spend the time and money needed to achieve accuracy. 24/07/2024 10
- 11. • Accuracy may be affected by sampling error and systematic bias • Sampling errors (random errors) are the random variations in the sample estimates around the true population parameters. • The error that results from taking one sample instead of examining the whole population. • It is resulted b/c of using sample for study. It can be eliminated in census study. • increase the sample size can improve the precision. • Increasing the size of the sample has its own limitations. Thus, the effective way to increase precision is usually to select a better sampling design. 24/07/2024 11
- 12. •A systematic bias (non-sampling error) • It comes from sources such as sampling frame error, mistakes in recording responses, or nonresponses from persons who are not contacted or who refuse to participate • it occurs in all surveys, whether in sample survey or census surveys. • Factors of systematic Bias are • Defective measuring device • Resulted b/c of measuring device error and defectiveness. • E.g. questionnaire or the interviewer biasedness, 24/07/2024 12
- 13. • Non-respondents • unable to sample all the individuals initially included in the sample • Natural bias in the reporting of data • People in general understate their incomes if asked about it for tax purposes, but they overstate the same if asked for social status or their affluence • Errors in Data • can occur because of distortions in the data collected or from mistakes in data coding, analysis, or interpretation of statistical analysis 24/07/2024 13
- 14. •Ways to reduce data error •Ensure that survey instruments are well prepared, be simple to read, and easy to understand. •Properly select and train interviewer to control data gathering bias or error. •Use sound editing, coding, and tabulating procedures to reduce the possibility of data processing error. 24/07/2024 14
- 15. Criteria of …… Cont. •Resources • If the researcher’s financial and human resources are restricted, certain options will have to be eliminated. • E.g. For a graduate student working on a conducting a national survey is impossible b/c of limited resources. • Managers concerned with the cost of the research versus the value of the information ………. save money by using a nonprobability sampling design rather than make the decision to conduct no research at all. 24/07/2024 15
- 16. Criteria of …… •Time • A researcher who needs to meet a deadline or complete a project quickly will be more likely to select a simple, less time-consuming sample design. •National versus Local Project • Geographic proximity of population elements will influence sample design. • When population elements are unequally distributed geographically, a cluster sample may become much more attractive. 24/07/2024 16
- 17. Criteria of …… •Advance Knowledge of the Population • Advance knowledge of population characteristics, • such as the availability of lists of population members, is an important condition. • In many cases, however, no list of population elements will be available to the researcher. • A lack of adequate lists may lead to use sampling techniques which do not require sampling frame. 24/07/2024 17
- 18. Types of sample design • There are two basic types of sampling techniques / methods/ designs. They are • Probability sampling techniques: is based on the concept of random selection • Non-probability sampling techniques: is nonrandom sampling • The nature of research study will determine the type of sampling to be used. • E.g. • Large-scale descriptive studies almost always use probability- sampling techniques. • Qualitative studies almost always use non-probability samples. 24/07/2024 18
- 19. Probability Sampling Methods •is also known as ‘random sampling’ or ‘chance sampling’ •every element in the population has equal (nonzero) chance of being selection. •Elements are not selected by the choice of the researcher, but by means of certain procedures. •Removes human judgment from the sampling process and ensure a more representative sample. •Researchers use a randomization process in order to reduce or eliminate sampling bias. 24/07/2024 19
- 20. •The five basic types of sampling methods are: •Simple random sampling, •Systematic sampling, •Stratified sampling, •Cluster sampling, •Multi stage sampling 24/07/2024 20
- 21. Simple Random Sampling (SRS) • It must give an equal chance of being selection for each element of a population • Two methods are used to pick a sample : lottery method or a random number table method. • Lottery Method in SRS • Steps • Write all names on a slip of paper (set a ticket) with numbers corresponding to the number of populations • Place the slips in a container • Shack the container to mix up the slips • Select the slip from the container until the desired number is selected • Random Number Table Method in SRS • A random number table is a table of random numbers or random digits. It is numbering all individuals in the population 24/07/2024 21
- 22. Systematic Sampling • A sampling procedure in which a starting point is selected by a random process and then every kth number on the list is selected. • To avoid any possible human bias in using this method, the researcher selects the first element randomly. • Samples are chosen at regular intervals from the sampling frame • Steps • identify & defining the population • determine the desired sample size • obtaining a list of the population • determine what sampling interval k is equals to k= population size (N)/sample size (n) 24/07/2024 22
- 23. •select a random no b/n 1-k (sampling interval) by picking one out of 1-k •starting at that point, take every kth name on the list until the desired sample size reached. •E.g. Given N= 1,000 n=200 •k= 1,000 200 = 5 the sampling interval is 1-5. •According to step 5, if the selected no is 4th item, then the sample would include 9th, 14th, 19th, etc. 24/07/2024 23
- 24. Stratified Sampling • The researcher divides the population into homogeneous groups (called strata, singular stratum) and randomly selects subsamples from each group. • Stratification would be based on the principal variable under study. • It should be ensured that all subgroups in the accessible population are represented in the sample. • It is applicable if the population is heterogeneous; however homogeneity can be achieved through dividing the heterogeneous population into homogeneous sub population (strata). 24/07/2024 24
- 25. •In allocating the sample size to each stratum, we usually follow proportional allocation, i.e. the sample size from each stratum is proportional to the size of the stratum. • nk = ( 𝑁𝑘 𝑁 )𝑛 = 𝑛 𝑁 (𝑁𝑘) • Where n1 = sample size to find; nk = sample size for the kth stratum; Nk = population size of the kth stratum; n= total sample size (n=n1+n2+n3+…+ nk); N= total population (N=N1+N2+N3+…+Nk) 24/07/2024 25
- 26. Cluster Sampling • If the population is heterogeneous, very large or resides in a large area, it is costly and time consuming to take samples by using the above three methods. • It divide the area into a number of smaller non-overlapping areas and then to randomly select a number of these areas. • Cluster sampling is used • when population is very large; • a list of the number of population doesn’t exist; and • the population is widely scattered. • Cluster sampling randomly selects groups but not individuals. The selected members in the group (called clusters) have similar characteristics with other groups. 24/07/2024 26
- 27. Difference between stratified and cluster sampling •Stratified sampling is used when each group has small variation within itself but there is a wide variation between the groups. •We use cluster sampling in the opposite case; when there is considerable variation within each group but the groups are essentially similar to each other. •In stratified sampling the elements are selected from each group randomly. •In cluster sampling, a number of the subgroups are selected for the study. 24/07/2024 27
- 28. Multi-Stage sampling • It is a further development of the principle of cluster sampling. • It is used in large-scale surveys for a more comprehensive investigation. • is used when the reference population is large and widely scattered. • A multistage sampling has more sampling errors than a one- stage sample. • Primary sampling units are selected randomly and secondary sampling units will be selected from PSU and a like. 24/07/2024 28
- 29. 24/07/2024 29
- 30. Non-Probability Sampling Methods • Refers to the selection of a sample that is not based on known probabilities. • Not every unit in the population has a chance of being included in the sample. • Easier, quicker and cheaper to carryout than probability designs. • Subjective judgments play a role in selecting the sampling elements. • Procedures are not valid for obtaining a sample that is truly representative of a larger population. • Tend to over-select some population elements and under-select others. 24/07/2024 30
- 31. Types of non-probability sampling •There are four common non-probability sampling methods •Convenience Sampling •Purposive Sampling •Quota sampling •Snowball sampling 24/07/2024 31
- 32. Convenience sampling •Is also referred to as haphazard Sampling or accidental sampling. •Involves including in the sample whoever happens to be available at the time. •the primary concern is chosen samples with no difficulty of access. •It identifies and selects anyone who is convenient. •Elements are included in the sample without pre- specified or known probabilities of being selected. •Produce ineffective, highly unrepresentative samples and is not recommended. 24/07/2024 32
- 33. •Convenient sampling is used •When the universe is not clearly defined •When sampling unit is not clear •When a complete source list is not available 24/07/2024 33
- 34. Purposive/judgmental Sampling • Samples are selected based on researcher experience or prior knowledge of the group to be sampled. • The researcher uses his own judgment about which respondent to choose and • It selects cases with specific purpose in mind or Pick only those who best meet the purposes of the study. • Mostly used in qualitative researches. 24/07/2024 34
- 35. Quota Sampling • Interviewers are given quotas to be filled from different strata. • The actual selection of the items is left to the interviewers’ discretion. • In quota sampling a research first identifies categories of people (e.g., male, female) • Then decides how many to get in each category. • Thus, the number of people in various categories of the sample is fixed. • Therefore, the interviewer has a quota to achieve from each category. 24/07/2024 35
- 36. •As there is no element of randomization, the extent of sampling error cannot be estimated. •Misrepresentation is possible because haphazard sampling is used within the categories. •B/c nothing prevents the researcher from selecting people who act friendly or who want to be interviewed. 24/07/2024 36
- 37. Snow ball sampling • It referred as Networking sampling or network, chain referral, or computational sampling. • Begins with one or a few people or cased and spread out on the basis of links to the initial case. • is a method for identifying selecting the cases in a network. • selecting a few people who can identify other people and who might be good participants for a study in which the participants are scattered or not found in clusters. • mostly used during interviewing in which one respondent recommends another potential person that could give information. 24/07/2024 37
- 38. 24/07/2024 38
- 39. THE END 24/07/2024 Aytenew Temesgen 39
Editor's Notes
- #3: Sampling is the process of using a small number or part of a larger population to make conclusion about the whole population.
- #5: Sampling unit is element or set of elements considered for selection in some stage of sampling. Sampling unit may be a geographic one (state, district…); a construction unit (house, flat…); a social unit (family, club, school…) or individuals.
- #6: the populations of fish, birds, mosquito etc… are large and constantly moving, being born and dying. Therefore, we just take some samples to do a research as it is impractical to have a census upon such types of populations.
- #11: Accuracy refers to correctness, precision, accurateness and exactness of samples estimation about the population