THE UNFOLDING TRAGEDY OF INDIAN DATA

There is very little recognition of the extent to which our understanding of the economic and social characteristics of our country depends on sample surveys conducted by various government statistical agencies, particularly the National Sample Survey Office (NSSO).

- Pronab Sen

Practically all social indicators, except a very few collected in the Population Census, are obtained from surveys. As far as the economy is concerned, nearly half our GDP comes from the informal sector, including agriculture. Since people in the informal sector do not maintain detailed books of account, surveys are the only way to get the necessary information. So, in the absence of quality surveys, we will have practically no idea about the full economic and social development of our country.

Quality surveys depend on two critical elements. First, it should be possible to extrapolate data from a very small sample to the country as a whole. This is done with the use of ‘sampling frames’, which are very large data sets covering the entire country, and from which the sample is drawn in a representative manner. In India, there are two primary sampling frames: i) the Population Census, carried out once every 10 years and ii) the Economic Census, once every five years. Almost all surveys depend on one or the other. These frames need to be updated periodically to ensure that they accurately reflect the present position; if they are not, surveys based on them will give misleading estimates.