Statistical Theory

The word 'statistics' appears to be originating from the Latin word 'status' or the Italian word 'statista' or from the German word 'statistik'.  Each of them refer to a political state.  In olden days the government used to conduct surveys to get information regarding population and property and wealth of the country.  Such data were called statistics in course of time.  The methods of collecting and interpreting data are called statistical methods and are studied under a science called 'statistics'.  We can thus say that we compute 'statistics' (data in secondary form) from 'statistics' (data in primary form) with the help of 'statistics' (the science).

 

In India, the collection of important data by government was done nearly 2400 years ago.  These indications are found in Kautilya's Arthashastra.  In Germany, systematic collection of administrative statistics was in force in the 18th century and in Britian in the 17th Century.  The theoretical development of so called modern statistics got a thrust only in the seventeeth century when the Theory of Probability came into existence. 

 

Significant contributors in the development of statistics include Pascal, Bernoulli and De-Moivre in the seventeenth century resulting in the Pascal's theorem, the theory of probability and the Normal Curve.  In the eighteenth century, Laplace independently arrived at the same results.  In the nineteenth century, Gauss, Quetlet, Bayes, Khintchine and Galton developed the constancy of numbers, sampling and the theory of regression.  Further in the same period, there was Pearson who developed the Chi-Square test and Bowley and Gosset who made additional contributions.  In the twentieth century, Sir Ronald Fisher made a major contribution in the field of experimental design with his 'Design of experiments'

 

Merits of statistics

 

           Statistics help in developing sound methods of collecting data so that the data collected can be used to draw the valid reference regarding the desired objectives.

           It presents the data in definite form, more often the numerical form.

           It helps in simplifying the complex data by way of classification / tabulation / graphical representation.

           The tabular/graphical representation of data and other complex statistics help in comparison.

           Statistics can be used to study the relationship between two or more factors.  The use of such relationship can be made in estimating one factor when the other(s) are known.

           It helps in the testing of hypothesis and in developing new theories.

           The data regarding a characteristic for a series of past periods can be used to forecast its value for a future period.

           It is invaluable to Research & Development methodologies.

           The powerful function of forecasting leads us to the need of planning and thus facilitates in formulating policies and helps in planning and to implement these policies.

 

Limitations of statistics

 

           Statistics is a very powerful science to study quantitative data.  But the limitation is that it deals only with quantitative data.

           Statistics is used to draw conclusions regarding a group of units rather than a single unit.

           The inferences are true only on an average and not when applied individually.

           It is only a tool and not an end in itself. 

           The inference drawn could be biased possibly due to an element of bias sometimes involved in the collection of data.

           Misinterpretations could sometimes result if the desired skill is absent or if it is used unethically or ineffectively.

           Misuses could result from lack of knowledge, faulty or misleading interpretation of data, incorrect or flawed base data or inadequate or incorrect analytical methodology adopted.