Data on daily Log returns of the NIFTY 50 index in the National Stock Exchange India

Abstract: India is one of the major emerging markets. We report daily log return percentages of the NIFTY 50 index in the National Stock Exchange in India, from the index base date of 3rd November 1995 to 31st March 2018. The NIFTY 50 index is a diversified fifty stock index accounting for twelve sectors of the Indian economy. It is used for a variety of purposes such as bench-marking fund portfolios, index based derivatives and index funds. The daily log returns of an index are the natural logarithms of the ratios of the closing values of the index on consecutive trading days over a certain period of time. The daily log return percentages are simply the log return values multiplied by hundred. The log return data are widely used in empirical finance to assess risk and return on investments, for estimation market risk, back testing of market risk measurement procedures, for modelling volatility and testing efficiency of financial markets. Data Format: The data are reported in twenty three csv spreadsheet files. The first csv file contains log return percentage data from 3rd November 1995 to 31st March 1996 from. The remaining twenty two csv files contain log return percentages from 1st April 1996 to 31st March 2018. Each of the csv files contains date, closing value and log return percentages of the NIFTY 50 during a financial year. The name of the csv file indicates the financial year. Value of the data • To assess risk and return on investments in the Indian equity market. • To estimate and forecast market risk in terms of Value at Risk, Expected Shortfall, Median Shortfall of the NIFTY50 index. • Modelling volatility using GARCH type models. • Testing efficiency of the Indian equity market. • Benchmarking the performance of a portfolio with the NIFTY 50 index. • Estimating the chance of extreme daily returns of the NIFTY 50 index. Some observed empirical properties of the NIFTY 50 log return data. 1. Absence of autocorrelations: (linear) autocorrelations of the daily log returns seem to be insignificant beyond a time lag of one day. i.e. the linear correlation between log returns of the t th and t+h th trading days seems insignificant, for h exceeding 1. 2. Slow decay of autocorrelation in absolute returns: the autocorrelation function of the absolute values of the daily log returns remain positive for time lag upto 30 days. This suggests non linear dependence among the NIFTY 50 daily log return values. 3. The data is Leptokurtic, with extreme daily log returns (exceeding 5 percent in absolute value) present 4. Heavy tails: the (unconditional) distribution of returns seems to display a power-law or Pareto-like tail, with a tail index which is finite, higher than two. However the precise form of the tails is difficult to determine