Statistics Day Conference - July 5, 2011

The Reserve Bank of India organised the 5th Statistics Day Conference on July 5, 2011. Statistics Day marks the birth anniversary of Prof. P.C. Mahalanobis, the legendary statistician who contributed enormously on the development of statistics and statistical infrastructure in the country. On this occasion, distinguished statisticians viz., Prof. Sastry G. Pantula and Prof. Rajeeva L. Karandikar spoke on topics relevant to statistical analysis in central banks such as time series and financial statistics.

Recounting the value of immense contributions of Prof. P. C. Mahalanobis in Statistics, Dr. D. Subbarao, Governor, Reserve Bank of India in his inaugural address highlighted the relevance and importance of statistics and statistical analysis to support policy formulation. He emphasised that policy calibration, be it monetary policy, regulatory actions or decisions in pursuit of financial stability, is improved by the quality of data at our command and our ability to analyse and interpret that data.;Citing an example of the new series of index of industrial production (IIP), Governor indicated that while the new series is consistent with the other related indicators, the old series was contrary to the underlying trend of the deceleration after the global financial crisis. The new series also shows that there has not been an industrial slowdown in the second half of 2010-11, contrary to the indication of the old series. Referring to the interpretation of inflation data, Governor indicated that WPI has been opted as a second best choice in absence of a single CPI representing the whole country. Further referring to RBI’s preference for non-food manufactured product inflation as an indicator of demand side pressure, Governor indicated that core inflation is a derived measure from the headline inflation which is designed to capture the persistence component of inflation and amenable to policy. While it is true that commodity prices influence the non-food manufactured products component of WPI, it is also true that the pass-through from higher commodity prices to WPI depends critically upon the underlying demand conditions in the economy. In this context, Governor welcomed the compilation of new CPI (rural and urban). However, there is a need for a longer time-series data for making them suitable for policy purposes.

Drawing upon the basic principle that drove Prof. Mahalanobis in his use of data and statistical analysis, Dr. Subir Gokarn, Deputy Governor emphasised the need for understanding of the various actors at play and various inter-relationships between them for effective decision-making. In the context of policy challenges and analytical complexities faced by the Reserve Bank, he highlighted the need for understanding the structural breaks for better assessment of the ever evolving economy. He also highlighted the merits of triangulation i.e. approaching a problem from three different dimensions that allows one to draw a boundary around the set of reasonably accurate assessments of the situation, which then make the leap to the policy decision manageable. The first of these is the data from household surveys that are conducted regularly providing inputs to the forward looking decision-making process. The second side relates to the understanding of the business cycle indicators from the company surveys. The third side of the triangle is an extensive consultation process, with banks and other financial institutions, manufacturing and service companies, various industry associations and professional economists. Thus, effective triangulation represents an efficient alignment of three different dimensions of data and decision-making.

While welcoming the participants, Shri Deepak Mohanty, Executive Director briefly discussed the role and responsibilities of the statisticians in Reserve Bank of India. He stressed the need for timely and accurate data, dissemination of data on real time basis, maintaining global standards, need for a quarterly policy model using DSGE framework, assessment of asset prices, data on employment and surveys for the assessment of the Reserve Bank’s financial inclusion initiatives.

Prof. Pantula, in his keynote address, emphasised the value of time-series modeling for central banks. However, he cautioned at the lack of understanding the true data generating process and application of alternative testing models consistent with the underlying economic dynamics. Prof. Karandikar emphasised the limitations of using Gaussian model for the bulk of the financial risk solutions. While the tail of the distribution could be suitably captured by alternative modeling techniques, forecasting of black swan event like the recent financial meltdown is not practically possible.

Based on the theme, the conference had technical sessions on time series analysis and financial statistics where internal research papers highlighting various aspects like growth inflation nexus, financial conditions index, credit risk modeling, and portfolio selection were presented.

R. R. Sinha
Deputy General Manager

Press Release : 2011-2012/27