Ans : There are various types of sampling but all types are not equally appropriate and important for a particular type of enquiry. The important methods of sampling are as follows:
i. Probability sampling
ii. Non-probability sampling
(i) Probability sampling
Ans:- Probability sampling is a scientific method of selecting samples according to some law of chance in which each unit in the population has some potentiality of being selected in the sample. There are various types of probability sampling which are discussed below:
A) Simple random sampling:- In this method, samples are drawn one by one with some chance of being selected. Simple random sampling can be administered by lottery method or by using a table of random numbers.
Merits
a) It is free from human bias.
b) The maximum information can be obtained in short period of time at minimum cost.
Demerits
a) The sample drawn by this method may not represent the population if the sample size is not sufficient large.
b) The sample drawn by this method may be highly scattered. So, it may be quite time-consuming and costly.
B) Stratified sampling:- In this method of sampling the entire population is divided into two or more homogeneous groups known as strata. Then a simple random sampling procedure is used to draw samples from each stratum. Suppose, there are altogether 140 people studying in a college which is having three different stream. If 50 people are studying +2, 50 are studying BBA and 40 are studying MBA. Then we can make three group as:
Suppose if we want total of 50 people for our survey, then by simple random sampling we select from all different groups as:
Merits
a) It gives more representative sample
b) The stratification reduces the cost and administration difficulties.
Demerits
a) The process of stratisfication takes more time and money.
b) It may give wrong conclusion.
C) Systematic sampling:- In systematic sampling, first the units are arranged into some systematic order they a sample unit is selected by using simple random sampling technique. After this, the remaining sample units are selected of a definite interval. The sampling interval is calculated as:
Suppose there are 40 students In a class and we want to take a sample of 5 students using systematic sampling. Then for interval we can use
= 8
It means we have to select one student out of every 8 student. The first person is selected by using simple random sampling and then remaining will be selected systematically of 8th interval. So, if 1st selected student is 4th student then
4th
12th (4+8)
20th (12+8)
28th (20+8)
36th (28+8)
Merits
a) This method is simple and systematic.
b) Takes less time and labour.
Demerits
a) It requires complete information about the population.
b) Sample may not represent the population if the population listing is biased.
D) Cluster sampling:- In cluster sampling, the entire population is divided into groups called clusters and then select a random sample of these clusters. The clusters are divided in such a way that the characteristics within the clusters are a heterogeneous and between the clusters are homogeneous.
In cluster sampling, the term cluster refers to a natural but heterogeneous and complete grouping of the members of population.
Merits
a) It is easier, faster and more convenient than stratified.
b) It is useful when the population under study is infinite.
Demerits
a) The reliability decreases with the increase in cluster.
b) Not appropriate when population size is large.
E) Multi-stage sampling:- In this method, sampling is done in various stage. Multistage sampling is a further development of cluster sampling.
Merits
a) More flexible than other methods
b) This technique reduces operational cost.
Demerits
a) It is less efficient than other.
b) Errors are likely to be larger than other methods.
(ii) Non-probability sampling
Ans:- A sampling procedure in which the sample is choose on the basis of convenience, personal judgement etc. of the investigator. There are various types of non-probability sampling they are:
a) Judgement sampling:- In this method, the desired sample is drawn on the basis of judgement of investigator. He selects those units which are appropriate for the objective of the survey.
b) Quota sampling:- This method is used when data is large and making investigation concerning public opinion. A definite quota is fixed for each social class, different age groups, different regions etc. for interview within that quota. From each group, Sampling involves the representation of the entire population and each group has its proper representation in the sample.
c) Convenience sampling:- Convenience sampling is the method of selecting sample not by judgement of the investigator but because the elements in a fraction of the population can be reached conveniently.