By Ajay Kumar Gupta
In the words of Prof. PC Mahalanobis “Statistics must have a clearly defined purpose, one aspect of which is scientific advancement and the other human welfare and tiol development.” And in both the aspects his contribution has been immense. He is rightly referred to as the chief architect of Indian statistical system as well as father of statistical science in India.
What started as a chance encounter with the jourl Biometrica, turned into a passion so strong that it not only helped in building a strong statistical community in India but also lead to advancement of many theoretical works in the field. Prof. Mahalanobis had to face opposition and challenges in his initial endeavours to establish statistics as a mainstream discipline of study and research.
However, he persisted in his efforts and witnessed, contributed in no small measure by himself, change in perception of statistics in academic and public circles. We get a glimpse of this in the introductory part of his oft-quoted speech in the 1950 session of Indian Science Congress “Why Statistics?”:
“I discussed with a friend of mine, …..the possibility of having a separate section for Statistics… A little later he informed me that there was no chance of my proposal being accepted, and with a smile told me that some of his colleagues had remarked: “If statistics is to have a section, you may as well have a section for astrology”. Evidently, statistics and astrology were bracketed together in the mind of many of our scientists. The forecasting of future events is, of course, a common feature; and the basis was felt to be equally unscientific... A great change has taken place in the climate of scientific and public opinion about statistics.”
Mahalanobis set up the Indian Statistical Institute as a learned society on 17 December 1931, which was registered in April 1932 as a non-profit distributing learned society under the Societies Registration Act.
All or nearly all the statistical work done in India during the 1920s and until the mid-1930s was done single-handedly by Mahalanobis. The early statistical studies included alyses of data on stature of Anglo-Indians, meteorological data, rainfall data, data on soil conditions, etc.
Some of the findings of these early studies were of great impact in the control of floods and development of agriculture. His alysis of anthropometric data led to the famous concept in Statistics known as ‘Mahalanobis Distance’. During 1937-45, he introduced several innovative techniques and preferred to call them “experiments in statistical sampling”. He started his work on sample surveys with estimation of area and yield of jute crop in Bengal in 1937.
However, it was not easy for him to get these estimates accepted;controversy between him and the advocates of complete enumeration continued for over a decade. Ultimately he was able to demonstrate that estimates based on sample surveys were often more accurate than those based on complete enumeration, and that sample surveys could yield estimates with small margins of error within a short time and at a smaller cost than complete enumeration.
Mahalanobis was always interested in the “promotion of scientific research and fruitful applications of research results to problems of social welfare. These applications of statistics were not only in agriculture where he pioneered crop cutting experiments, but also in Industry.
Mahalanobis’s contributions to large scale sample surveys are among his most significant and lasting gifts to statistics. Given the paucity of administrative data, and the possibility of biases creeping in, the strategy Mahalanobis envisaged in his notes to the Nehru cabinet on creating credible data sets were based on representative sample surveys, economist Ashok Rudra writes in his biography of Mahalanobis. To establish the credibility of surveys, he, who was a big proponent of cross-examition of data, invited some of the pioneers of statistics to review the work done at ISI.
The first review committee of NSS included such intellectual giants as RA Fischer, MH Hansen, T Kitagawa, A Linder and F Yates. Their opinion was not entirely uncritical but it noted in its report that in the matter of sample surveys, “those outside India must expect to have more to learn than to teach”.
The three notable contributions to the theory and practice of sample surveys by Mahalanobis are “pilot surveys, optimum survey design and Inter Penetrating Network of sub-samples technique (IPNS)” (cf. Lahiri, 1973). He always advocated Inter penetrating network of sub-samples (IPNS) theory both in conduct of large scale sample surveys as well as in working of government administration where he did not approve of the fact that it was regulated by principle of authority.
Mahalanobis was very much concerned with errors at various stages of data collection and alysis and insisted on cross examition of data. He applied IPNS for assessment and control of errors, especially non-sampling errors, in surveys. His technique of IPNS was appreciated by both the statisticians as well as politicians. The concept of pilot surveys was a forerunner of sequential sampling developed by Abraham Wald, as acknowledged by Wald in his book.
In addition to introducing these concepts, Mahalanobis raised important and difficult philosophical questions on randomness and representativeness of a sample, which remain relevant and challenging even today. Besides being a reputed academician, Prof. Mahalanobis was a great administrator who stood up for what he believed in. When he was asked by a young colleague as to what was the most important quality for a great administrator he replied, “The capacity to be unpleasant when the occasion called for it.” We get another picture of him in W Edwards Deming’s remark “He never permitted difference of opinion to impede the advancement of someone with an opposing view.”
One of the first tasks after India gained independence was to reassess the size and ture of the Indian economy and the man chosen to head the mission was statistical genius Prof. Mahalanobis. The committee included eminent scientists like Rao and Gadgil. The result was a voluminous report on tiol Income. Prof. Mahalanobis’ administrative qualities and the ability to convince people resulted in him playing a leading role in creating a statistical edifice for the country.
Although remembered today largely as the architect of India’s five-year plan model, PC Mahalobis, as the honorary statistical adviser to the cabinet, had a greater contribution in building a new statistical architecture for the country. He helped establish the Central Statistical Organisation (CSO), the tiol Sample Survey (NSS) and the Annual Survey of Industries (ASI), all of which were run from ISI in the early years. (PIB)