Statistical Method Vs. Experimental Methods

Man acquires knowledge form a variety of sources. In early time, it was believed that acquiring knowledge was a matter a change and it sources were unknown. But the tremendous advance in human knowledge that has taken place in the last two centuries is mainly due to the adoption of systematic methods and not just a matter a chance. Such methods as are systematically used in enlarging knowledge are known as scientific methods.

There are two primary method employed for advancing knowledge, namely, experimental methods and statistical methods. Experimental methods are the best known of scientific methods and have been historically most fruitful. Under this method, cause and effect relations are often established or investigated within a controlled set-up in the laboratory. In order to determine the effect of a change in supply of wheat in its price, it would be necessary to ensure that tastes of people, attitude of trader to change in supply, disposable funds of people, etc., can be studied in isolation. However, these factors are so inextricably bound up with each other that it would be very difficult to isolate any one of them for experimental purposes.

It would be wrong to ignore altogether those fields. Here experimental methods cannot be applied. In such cases resort may be had to statistical methods. In applying statistical methods a problem is studied systematically as in the experimental methods, but the system used is not the same. Without an adequate understanding of statistics, the investigators in social sciences may frequently be like the blind man groping in dark closet for a black cat that isn’t there. The methods of statistics are useful in an ever-widening range of human activities in any field of thought in which numerical data may be had.”

However, it should be noted that the distinction between the experimental methods and the statistical methods is somewhat formal and arbitrary and should not be taken as anything rigid and definite. In practice, the scientists often combine elements of both experimental and statistical approaches.