SAMPLING Sampling is defined as the process of learning about population on the basis of sample drawn from it. In it, a part of universe is studied who represent the whole population because it includes all the characteristics of whole universe.SAMPLING There are various probability and non-probability sampling methods which are used to collect the data from sample of items selected from population and conclusions are drawn from them. These are known as sampling techniques. For example, if some-one wants to purchase a carton of apples, he will examine only one or two from the whole lot and on that basis he will examine only one or two from the whole lot and on that basis he will decide whether to purchase the carton or not.SAMPLING: SOME BASIC CONCEPTS UNIVERSE OR POPULATION: In statistics, universe or population means an aggregate of Items about which we obtain information. A universe or population means the entire field under Investigation about which knowledge is sought. For example, if we want to collect information about the average monthly expenditure of all the 3,000 students of a college, then the entire aggregate of 3,000 students will be termed as Universe or Population.SAMPLING: SOME BASIC CONCEPTS UNIVERSE OR POPULATION: A population can be of two kinds (i) Finite and (ii) Infinite. In a finite population, number of items is definite such as, number of students or teachers in a college. On the other hand, an infinite population has infinite number of items e.g. number of stars in the sky, number of water drops in an ocean, number of leaves on a tree or number of hairs on the head.SAMPLING: SOME BASIC CONCEPTS SAMPLE: A part of population is called sample. In other words, selected or sorted units from the population is known as a sample. In fact, a sample is that part of the population which we select for the purpose of Investigation. For example, if an investigator selects 200 students from 2000 students of a college who represent all of them, then these 200 students will be termed as a sample. Thus, sample means some units selected out of it population which represent it.SAMPLING TECHNIQUES The method of selecting a sample out of a given population is called sampling. In other words, sampling denotes the selection of a part of the aggregate statistical material with a view to obtaining information about the whole. Now a days, there are various methods of selecting a sample from a population in accordance with various needs.SAMPLING TECHNIQUES 1. Probability Sampling Methods: (1) Simple Random Sampling (2) Stratified Random Sampling (3) Systematic Random Sampling ; (4) Multistage Random Sampling 3 (5) Cluster Sampling 2. Non-Probability Sampling Methods: (1) Judgement Sampling (2) Quota Sampling (3) Convenience Sampling (4) Extensive SamplingPROBABILITY SAMPLING METHODS Probability sampling methods are such methods of selecting a sample from the population in which all units of the universe are given equal chances of being included in the sample. There are various variants of probability sampling methods, which are given in the following slides.PROBABILITY SAMPLING METHODS (1) SIMPLE RANDOM SAMPLING: Simple random sampling is that method in which each Item of the universe has an equal chance of being selected in the sample. Which item will be included in the sample and which not, such decision is not made by an investigator on his will but selection of the units is left on chance.PROBABILITY SAMPLING METHODS According to random sampling, there are two methods of selecting a random sample: (i) Lottery Method: In this method, each unit of the population is named or numbered which is marked on separate piece of paper. Such chits are folded and put into some urn or bag. Thereafter as many chits are made selected by some person as many units are to be included in a sample, (ii) Tables of Random Numbers: Some experts have constructed random number tables. These tables help in selection of a sample. Of all such various tables, Tippett's Tables are most famous and are in use. Tippett has constructed a four-digit table of 10,400 numbers. In this method, first of all, all the items of a Population are ae serially. There after by making use of Tippett's tables, in accordance with the size of the sample, numbers are selected.PROBABILITY SAMPLING METHODS (2) STRATIFIED RANDOM SAMPLI This method is used when units of the universe are heterogeneous rather than homogenous. Under this method, first of all units of the population are divided into different strata in accordance with their characteristics. Thereafter by using random sampling, sample items are selected from each stratum. For example, if 150 students are to be selected out of 1500 students of a college, then firstly the college students will be divided into three groups on the basis of Arts, Commerce and Science. Suppose there are 500, 700, 300 students respectively in three faculties and 10% sample is to be taken, then on the basis of random sampling 50, 70, and 30 ; will be selected by using random sampling. Thus qual representation to each class or group and e of being selected in the students respectively this method assumes © all the units of the universe get equal chance sample.PROBABILITY SAMPLING METHODS (3) SYSTEMATIC RAN Ml SAMPLING: In this method, all the items of the universe are systematically arranged and numbered and then sample units are selected at equal intervals. For example, if 5 out of 50 students are to be selected for a sample, then 50 students would be numbered and systematically arranged. One item of the first 10 would be selected at random. Subsequently, every 10th item from the selected number will be selected to frame a sample. If the first selected number is Sth item, then the subsequent numbers would be 15th, 25th, 35th and 45th.PROBABILITy SAMPLING METHODS 4) MULTISTAGE OM SAMPL When sampling procedure passes through many stages, then it is known as multi-stage Sampling. In this method, firstly the entire universe or population is divided into stages or sub-stages. From the each stage some units are selected on random sampling basis. Thereafter, these units are subdivided and on the basis of random sampling again some sub- units are selected. Thus, this goes on with sub-division further and selection on. For example, for the purpose of a study regarding Adult Education in first some districts will be selected on random basis. the selected districts, some tehsils and out of tehsils, ;wns may be thus selected, further out of the villages or bourhood, or wards and out of the wards, some from whom the inquiry will be made Punjab State, Thereafter out of some villages or to towns, some neigh households will be selected concerning the problem at hand.PROBABILITY SAMPLING METHODS () CLUSTER SAMPLING: In this method, the univ erse is simply divided into many groups called clusters and out of which a few clusters are selected on random basis and then the clusters are complete enumerated, This method is usually applied in industries like as in pharmaceutical industry, a machine produces medicines tablets in the batches of hundred each, then for quality inspection, a few randomly selected batches are examined.5 NON-PROBABILITY SAMPLING METHODS Non-probability sampling methods are those methods in which selection of units is made on the basis of convenience or judgement of the investigator rather than on the basis of probability or chance. In such methods, selection of units is made in accordance with the specific objectives and convenience of the investigator.-PROBABILITY SAMPLING METHODS 1) JUDGEME) T SAMPL| Under this method, the selection of the sample items depends exclusively on the judgement of the investigator. In other words, the investigator exercises his judgement in the choice and includes those items in the sample which he thinks are most typical of the universe with regard to the characteristics under study. NON For example. if a sample of 20 students is to be selected from a i ding habits of the 10 r analysing the spen the 1 as ou pear would select 20 students, who in his Students, the 1! i class. opinion are representative of theNON-PROBABILITY SAMPLING METHODS (2) QUOTA SAMPLING: In this method, the investigators are assigned definite quotas according to some criteria. They are instructed to obtain the required number to fill in each quota. The investigators select the individuals (i.e. sample items) to collect information on their personal judgements within the quotas. When all or a part of the whole quota is not available or approachable, the quota is completed by supplementing new respondents. . Quota sampling is a type of judgement sampling.NON-PROBABILITY SAMPLING METHODS (3) CONVENIENCE SAMPLING: In this, the choice of the sample is left completely to the convenience of the investigator. The investigator obtains a sample according to his / her convenience. For example, a book publisher selects some teachers conveniently on the basis of the list of the teachers from the college prospectus and gets feedback from them regarding his publication. This method is less expensive and more simple but is unscientific and unreliable. This method results in more dependence on the enumerators. This method is appropriate for sample selection where the universe or population is not clearly defined.NON-PROBABILITY SAMPLING METHODS (4) EXTENSIVE SAMPLING: In this method, sample size is taken almost as big as the population itself like 90% the section of the population. Only those units are left out for which data collection is very difficult or almost impossible. Due to very large sample size, the method has greater level of accuracy. , ayers i becomes possible but this metho dy of the problem Intensive study ry at disposal involves heavy resourceSAMPLING AND NON-SAMPLING ERRORS 1) SAMPLING ERRORS Sampling errors are those which arise due to the method of sampling. Sampling errors arise primarily due to the following reasons: (a) Faulty selection of the sampling method. (b) Substituting one sample for the other sample due to the difficulties in collecting the sample. (c) Faulty demarcation of sampling units. (d) Variability of the population which has different characteristics.SAMPLING AND NON-SAMPLING ERRORS (2) NON-SAMPLING ERRORS Non-sampling €rrors are those which creep in due to human factors which always varies from one investigator to another. These errors arise due to any of the following factors: (1) Faulty planning. (2) Faulty selection of the sample units. (3) Lack of trained and experienced staff which collect the data. (4) Negligence and non-response on the part of the respondent. (5) Errors in compilation. (6) Errors due to wrong statistical measures. (7) Framing of a wrong questionnaire. (8) Incomplete investigation of the sample survey.