It is important for the investigator to decide whether to use sample or census method for collecting data. The selection primarily depends upon the nature and extent of the enquiry and the degree of accuracy desired. At the same time, the scope of the enquiry, its cost, the time of enquiry, the selection and training of the enumerators etc. are also to be taken into account. Basically, accuracy and precision depends upon the human element. If the human element is perfectly impartial and unbiased then best results can be expected from either method. In the absence of it, the results may be distorted.
Both the methods of enquiry have their individual merits and demerits. For example the sampling method is suitable in case of large population, where as census method is preferred in case of small population. In this connection S. S. Zarkovie rightly observes, “complete enumeration presupposes the existence of certain minimum facilities; such as-funds, professional personnel, sufficient time etc. These facilities do not always exist and therefore, it sometimes becomes impossible to take a census. Similarly a recourse to sampling makes it possible to obtain information in a number of cases where a complete enumeration cannot be undertaken”. Both the systems of enumeration are useful and advantageous at different occasions. So both or any of these methods may be followed according to the need or environment.
Types of Sampling:
In the sampling method a representative group of items from the population are selected. These groups of items are called samples. These samples represent the whole universe. Therefore the selection of samples is crucial in this method. It is rightly said, “Samples are like medicines. They can be harmful when taken carelessly or without knowledge of their effects. Every good sample should have a proper label with instructions about its use”. So while selecting samples, a number of factors should be considered. Some of the important factors are:
i) the nature of the population
ii) the distribution of items in the population
iii) the characteristics to be studied
iv) availability of data
v) availability of both financial and human resources etc.
Considering these factors a choice is made regarding the type of samples to be used. Generally there are two methods of selecting samples
1. Probability sampling method or Random sampling method
2. Non- probability (purposive) sampling method
Probability sampling method :
Probability sampling is also known as choice sampling. Here each individual item of the population has same chance of being included in the sample. So here the selection of the units in the sample entirely depends on the chance factor. One does not know beforehand which units will actually constitute the sample. Probability samplings are of different types. Some of the important types of probability sampling are.
a) Sample random sampling
b) Systematic Sampling
c) Stratified Sampling
d) Cluster Sampling
e) Multi-stage Sampling
Let us discuss these types of sampling in brief.
a) Simple Random Sampling:
The most common type of probability sampling is simple random sampling. Here each individual population unit has the same chance of being included in the sample. Random sampling technique is suitable where the population is more or less homogeneous. Random selection implies a strict process of selection like that of drawing lotteries.
Generally, there are two types of simple random sampling namely
(i) Random sampling without replacement and
(ii) Random Sampling with replacement
In case if the items selected in any draw are not replaced in the population before making the next draw then it is called random sampling without replacement. For example in a pack of cards suppose one card is drawn at random. So it will be drawn out of 52 cards. If it is not replaced then the next card will be drawn from the remaining 51 cards and so on. On the other hand, if the items selected in any draw is replaced in the population before making the second draw then it is called ‘random sampling with replacement; In the above example if the card is replaced back in the pack after each draw than every time one card will be drawn from a pack of 52 cards.
Therefore, in case of random sampling without replacement the number of units in the population decreases after every draw. But with replacement the number of units in the population always remains constant.
In simple random sampling, sample units are selected in two ways namely by ‘tottery method’ or by the use of ‘table of random numbers’.