The word sample is used to describe a portion chosen from a given population. It is selected from population so that it represents that population. The sample is studied and the results so obtained are applied to the entire population. Note that population and universe is synonymous in the parlance of sampling. Samples and population can be analysed and studied mathematically by using techniques such as mean, median, mode and standard deviation.

We have been asked to find out whether the students of Saint Paul School do their homework on a daily basis. In order to find the answer to this query, we have to check the homework record of each and every student who studies in this school. This is a very difficult and time-consuming task.

Thus, we take all students in the consideration; we can take a sample of 20 or 50 students and do our calculations. We judge or make an estimate and apply that result to the entire school. Thus, all the students of the school would be called Population and a portion of 20 or 50 students would be called Sample.

Sampling is a simple technique in which, researchers try to learn about the population on the basis of a sample drawn from its gamut. We study only a part of the universe and conclusions are drawn by analysing this sample. The results obtained by doing so are applicable to the entire universe. In the sampling process, we can define three vital elements, as follows:


(a) Selecting the sample from the population to be studied

(b) Collecting the information

(c) Making a conclusion about the entire population.

Sampling is not a haphazard technique of statistical analysis. It has well-defined rules for selecting the sample from the population. The idea of sampling dates back to very old times. People used to buy wheat by checking a handful of wheat from the market. Even today, a doctor examines a few drops of blood and draws conclusion about the type of blood of the body (of his patient).


The values obtained from the study of a sample are called statistics. The values obtained from the population at large called Parameters.

Sample and following other terms are essential to understand the concept of sampling:

1. Population: This term is used by statisticians not only to denote people, but also to define or label all those items that have been selected for a research study.

2. Statistics: When various analytical techniques describe the characteristics of a sample, these are called Statistics.


3. Parameters: When various analytical techniques describe the characteristics of a population, these are called Parameters.

4. Researcher: He or she is an expert who wants to undertake a research project and wishes of collect data to make samples, analyse these samples, use statistical or Operations Research (OR) techniques and arrive at a conclusion (or a set of conclusions) about the population studied by him or her.

Features of Sampling

L It Must is Independent: All the items of a sample should be selected independently of one another. Further, all the items of the universe should have the same chance of being selected in the sample. This means that the selection of a particular unit in one draw has no influence on the probabilities of selection in any other draw.


2. It must have Homogeneity: This means that there is no difference in the nature of units of the universe and that of the sample.

3. It must be Representative: A sample should be so selected that it truly represents the universe, else the results obtained could be very misleading.

4 It must be Adequate: The size of the sample should be adequate; else it may not represent the characteristics of the entire universe under study.

Categories of Sampling


There are two major categories of sampling:

1.Random or Probability Sampling: Random sampling is also called Probability Sampling because the laws of probability can be applied to it. Note that the term ‘random sample’ is not used to describe data in a sample; it is a process used to select the sample from a population.

Random Sampling does not depend upon the existence of detailed information about the universe. It also provides such data as are unbiased. Also, we can measure the relative efficiency of different sample designs with random sampling methods.

Limitations of this type of sampling cannot be ignored either. It requires high levels of skill. Also, it consumes a lot of time for planning the process of actual sampling. The cost of execution of this sampling method is very high.


2. Non-Random or Judgment Sampling: This is a process of sample selection where we do not use random methods. A non-random sample is selected on the basis of judgment or convenience. There is no selection on the basis of probability considerations. The pattern of sample variability in the process cannot be known.