The sample technique of data collection, as pointed out above, is based upon certain principles, or laws which are popularly known as theories of sampling. These are depicted hare as under:
(i) The law of Statistical Regularity: It is a corollary to9 the main theory of probability which speaks of the mathematical expectations of the success, or failure of an event. Basing upon this, the Law of ‘Statistical regularity’ tells us that a random selection from a universe is likely to give a representative sample.
If a large sized sample is taken at random from a universe it is likely to possess the same characteristics as that of the universe. As such the law of statistical regularity rests on two important points viz.
1. Largeness of the sample size, and 2. Selection of the samples at random.
1. Largeness of the sample size: In order to keep space with the law of Regularity, it is required that the size of the sample should be fairly large. This is because, a large sized sample is more likely to represent the true characteristics of the universe, and thereby to provide better estimates of the parameters i.e. the various measures of the population viz. average, dispersion, etc. If the size of the sample is considerable small it may not be a true representative of the population.
2. Selection of the sample at random: The second important point which the law of regularity requires to be fulfilled is that each item of the sample should be selected at random, or per chance without giving any scope for deliberate selection on the part of the enumerators. By ‘selection at random’ we mean a selection in which each and every item of the population has the equal chance of being selected in the sample.
(ii) The law of inertia of large numbers
This law is an extension of the law of statistical regularity described above. According to this law “Large numbers are relatively more inert (constant) and stable than small ones, and therefore, other things remaining the same, as the sample size increases, the results tend to be more reliable and accurate.”
By taking a sample of large size, the chances of the stability and reliability of the results are enhanced. This is because, as the size of the sample increases, it approaches the size of the universe and, therefore, is likely to reveal more closely the characteristics of the population. In large numbers, there will be no violent fluctuations or variations, although, there might be some changes with the efflux of time.