Sampling
- 1. SAMPLING
- 2. SOME IMPORTANT TERMS. Population: The aggregate of all units pertaining to a study is called population Element: A member of a population is an element(subject) Sample: A part of the population is known as the sample Sampling: It is the process of drawing sample from a larger population Sampling frame: The list of sampling units from which a sample is taken is called the sampling frame
- 3. CHARACTERISTICS OF A GOOD SAMPLE 1. Representativeness: Represent the population 2. Accuracy: Degree to which bias is free from the sample 3. Precision: Precision is measured by SD and standard error 4. Adequate sample size ensures reliability
- 4. ADVANTAGES OF SAMPLING. 1. Reduces time and cost of research 2. Saves labour 3. Quality of study is often better 4. Produce quicker results 5. If population is infinite sampling is only procedure possible
- 5. LIMITATIONS OF SAMPLING Sampling demands a thorough knowledge of sampling methods and procedures. Complicated sampling plan requires more labour.
- 6. Classification of sampling methods Probability sampling Non probability sampling
- 7. PROBABILITY SAMPLING Probability sampling are those that clearly specify the probability or likelihood of inclusion of each element or individual in the sample .
- 8. CONDITIONS OF PROBABILITY SAMPLING The size of the parent population must be known to the investigator. Each element in the population must have equal chance of being included in subsequent sample. The desired sample size must be clearly specified.
- 9. Positive&negative points… Positive point :-The obtained samples are considered representative. Negative point : Certain amount of sampling error exists because there is a limited amount of the entire population.
- 10. Types of probability sampling… Simple random sampling Stratified random sampling Systematic sampling Cluster sampling Area sampling Multi-stage sampling Multi phase sampling Sampling with probability proportionate to size Replicated sampling
- 11. Simple random sampling A simple random sample selected from a population in such a way that every member of the population has equal chance of being selected and selection of any individual does not influence the selection of any other Random sample is a sample selected at random. Sample selection should be done in such a way that any bias on the part of the observer shall be avoided
- 12. PROCEDURE Enumeration of all elements in the population Preparation of a list of all elements Drawing sample numbers by using lottery method, tables of random numbers or a computer
- 13. Two methods for random sampling Lottery method Table of random numbers
- 14. LOTTERY METHOD All items of the universe are numbered or named on separates lips of paper of identical size and shape Slips are then folded Mixed in a container A blind fold selection Number of slips taken =desired sample size
- 15. TABLE OF RANDOM NUMBERS Several standard tables of standard tables of random numbers are available E.g.: Tippet’s table, Fisher’s table, Kendall’s table, Rao’s etc These tables are known as random sampling numbers Tables are used for getting random numbers corresponding to which we select from population
- 16. ADVANTAGES All elements in the population have an equal chance of being selected Easiest to study Most simple type of probability sample Does not require prior knowledge The amount of sampling error can be early computed
- 17. Disadvantages It is impractical because of non availability of population list If the size of the sample selected is small ,the results may not be reliable A simple random design may be expensive in time and money The size of the sample required to ensure its representativeness is usually larger under this type of study
- 18. Sampling error in this sampling is greater than other probability samples This technique does not ensure proportionate representations to various groups consulting the population The use of simple random sampling may be wasteful because we fail to use all the known informations about the population
- 19. Stratified random sampling In stratified random sampling ,we must devide the population into different subgroups known as strata Items in each stratum are homogeneous From each strata items are selected by simple random sample method This method has the advantage of a simple random sampling method Different groups in the population get representations It ensures greater accuracy
- 20. It is appropriate for large heterogeneous population Stratification ensures representation to all relevant subgroups Provides data for analyzing various subgroups.
- 21. Division of stratified sampling 1.proportionate stratified sampling 2. dispropotionate stratified sampling
- 22. Propotionate stratified sampling .. In propotionate stratified sampling ,number of items selected from each sample is propotional to size of each stratum Number of items taken from each stratum is on the basis of size of each stratum ( eg)
- 23. Advantages It enhances representativeness of the sample It gives higher statistical efficiency It is easy to carry out
- 24. Disadvantages A prior knowledge of the composition of the population is required This method is very expensive in money &time Identification of strata might lead to classification errors
- 25. Disproportionate stratified sampling Dispropotionate stratified random sampling where equal number of items is selected from each stratum ,irrespective of size
- 26. Advantages It is less time consuming It facilitates giving appropriate weightage to particular groups which are small but important
- 27. Disadvantages The sample may be less representative This method requires prior knowledge
- 28. Systematic sampling This method of sampling is an alternative to random sampling It consist of taking K th (or N th)item in the population after a random start with an item from 1 to K as the interval between sample units are fixed ,this method is also called fixed interval method
- 29. Advantages It is much simpler than random sampling It is easy to instruct the field investigations The method requires less time This method is cheaper than simple random sampling Easier to check whether every K th has been included in the sample Sample is spread evenly over the population It is statistically more efficient than simple random sampling
- 30. Disadvantage This method ignores all element between two K th elements selected As each element does not have equal chances of being selected ,the resulting sample is not a random one This method may sometimes gives a biased sample
- 31. Cluster sampling When population are scattered over a wider area and a list of population element is not readily available. Cluster sampling means random selection of sampling units consisting of population elements Cluster sampling - the subjects are selected in groups or clusters rather than randomly
- 32. Cluster sampling process Identify clusters Examine the nature of clusters Determine the number of stages
- 33. Advantages The method is much easier and more convenient to apply when large populations are studied or large geographic areas are covered The cost of this method is much less This method promotes convenience of field work Sampling does not require more time This method is flexible
- 34. Disadvantages The cluster may vary and this variation could increase the bias of the resulting sample The sampling error in this method of sampling is greater
- 35. Area sampling .. This is an important form of cluster sampling As the geographic areas are selected as sampling units in such cases their sampling is called area sampling Area sampling invariably involves multistage sampling and sub sampling Eg…
- 36. Multi stage sampling In this sampling is carried out in two or more stages The population is regarded as being composed of a number of first stage sampling unit First a sample of the first stage sampling unit is drawn From each first stage sampling units a sample of the second stage sampling units is drawn The procedures comes down to the final sampling units Appropriate random sampling method is adopted at each stage
- 37. Advantages It results in concentration of field work in compact small areas and consequently in saving time ,labour and money It is convenient ,efficient, and flexible than single stage sampling.
- 38. Disadvantages The procedure of estimating sampling error is complicated
- 39. Sampling with probability proportional size(PPS) If one primary cluster has twice as large population as another ,it is given twice the chance of being selected The PPS is a better method for getting a representative sample of population element in multistage sampling Not all clusters are the same size. Can weigh the clusters to equate the difference. Can weigh the chances of a cluster being selected
- 40. Advantages Clusters of various size gets proportionate representation PPS leads to great precision and a constant sampling fraction at the second stage
- 41. Limitation PPS cannot be used when the sizes of the primary sampling clusters are not known
- 42. Application Used in all multi stage sampling
- 43. Multi-phase sampling Multi phase sampling is different from multi stage sampling In multi phase sampling the different phases of observation relate to sample units of the same type
- 44. Replicated sample Replicated sampling involves selection of a certain number of sub samples rather than one full sample in a population
- 45. Advantages It provides simple means of calculating the sampling errors Its is practical
- 46. Dis advantages A disadvantage of replicated sampling is that its limits the amount of stratification that can be employed
- 48. II NON PROBABILITY SAMPLING
- 49. Non probability sampling Non probability sampling is one in which there is no way of assessing the probability of the element or group elements ,of population being included in the sample .
- 50. Important sampling methods.. Quota sampling Accidental sampling Judgmental sampling Snowball sampling purposive or deliberate Convenience sampling Self selection sampling
- 51. Quota sampling Quota sampling - quotas for certain types of people or organizations are selected as the sample Interviewers are required to find cases with particular characteristics E.g., certain number of teenagers, etc. Advantage– better than convenience; introduce some diversity disadvantage – It is nonrandom sampling
- 52. Accidental sampling Accidental sampling is a type of nonprobability sampling which involves the sample being drawn from that part of the population which is close to hand. That is, a sample population selected because it is readily available and convenient
- 53. The researcher using such a sample cannot scientifically make generalizations about the total population from this sample because it would not be representative enough This type of sampling is most useful for pilot testing Eg (shoping complex)
- 54. Judgemental sampling In judgement sampling, the researcher or some other "expert" uses his/her judgement in selecting the units from the population for study based on the population’s parameters.
- 55. Snow ball sampling Snowball sampling – an individual or group of individuals are sampled. They provide other sources to be sampled. Sampling snowballs into a large selection. Useful for hard to identify groups. E.g., study of criminal organizations May lead to biased sample Sociogram – a map of individuals and their references.
- 57. Purposive sampling Purposive sampling is the selection of items in accordance with some purposive principle the items are selected in accordance with that criterion
- 58. Convenience sampling method In this method investigator is the most important person The whole sample is picked up according to his convenience He decided what should or should not be included in the sample It is to be seen as to what is the availability ,accessibility as well as the command of the investigator
- 59. Sample is not picked up with the help of any scientific method. There is no preplanning for the preparation of a sample Obviously in research this method is quite undependable
- 60. Self-selection sampling Self-selection sampling – test yourself Often used in sensation/perception experiments Problems Lacks diversity Can be extremely biased