Phase wise scaling and trend pattern analysis of prime Indian stock market indices during last decade (original) (raw)

Relationship Between Usa and Indian Stock Markets: A Time Series Analysis

In the present work we have studied daily data of NASDAQ during the period 5 th February 1971 to 31 st January 2009, daily data of Dow Jones during the period 1 st October 1928 to 31 st January 2009 and daily data of SENSEX during 1 st July 1997 to 31 st January 2009 in order to investigate the relationship between USA and Indian stock markets. These three time series are here processed through Finite Variance Scaling Method which is a form of scaling in order to find the corresponding Hurst exponents. Study reveals that all the three series exhibit anti-persistent behaviour (short-memory process). Interestingly it is observed that the corresponding values of Hurst exponents are not significantly different from each other. We have also studied the autocorrelations with different lags for all these three series and study reveals that we have steady negative profile for autocorrelations of all the three indices.

Scaling Analysis of National Stock Exchange Index

The scaling behaviour of the daily national stock exchange index data during the time period from July, 1990 to July, 2008 is analyzed in the present paper. This data is here processed through Finite Variance Scaling Method which is a form of scaling in order to find the corresponding Hurst exponent. The study reveals that the present data of daily national stock exchange index exhibits a persistent trend (long memory process).

Stochastic Pattern of Major Indices of Bombay Stock Exchange

Regular Issue, 2019

It is interesting to get inside and draw a meaningful inference by studying the movement of various stock indices. Portfolio managers, analysts, and investors are very keen to know about the technical pattern of indices. They consider the stock market is one of the economic barometers or market indicators of an economy. Indian financial market has undergone radical and vital change during the past few years. The purpose of this study is to check stochastic movements in selected indices and to signify nexus and interdependency among one another by the virtue of econometric analysis. The study comprises of daily closing value from 1st April 2014-1st April 2018, including major indices i.e. S&P-BSE 100; S&P-BSE-200, S&P BSE-500, S&P-BSE:Large cap, S&P-BSE:Mid-cap, S&P-BSE:small-cap, and BSE-SENSEX. Moreover, typical econometrics tool Augmented Dickey-Fuller Test, Granger Causality Test, and Johansen Co-integration Test were implemented to conclude the result. The study is one of its kinds to analyze the static and pair wise relationship among seven BSE indices along with the direction of their expected future movement that would help practitioners, policy makers and investors in anticipating the future movement of the indices. The Dickey-Fuller and Johanson test administered to analyze unit root and co-integration among the series in long run, followed by Granger causality test to observe the route of the short term relationship among various indices. The tests reveal uni-directional and in some cases bi-directional causality in selected indices. Further, it has been observed that due to co-integration, prices of different indices can't move far away from one another [1]. This stochastic study delves volatility pattern of some major indices of Bombay stock exchange with the help of econometric tools. It clearly delineates nexus of all the indices and provided an explanation to appreciate concrete conduct of one series into a mutual relationship. Hence, investors or analyst may predict the movements, interdependency and their relationship in a significant manner.

Scaling Analysis of Prime Stock Exchange Indices of the Emerging Seven (E7) Countries

2012

The emerging seven (E7) countries represent the seven major emerging economies that are predicted to have much larger economies than the G7 countries by 2020. The term was coined by the PricewaterhouseCoopers in the Stern Review report, which was published on 30 October 2006. These seven countries are People's Republic of China, India, Brazil, Mexico, Russia, Indonesia and Turkey. In the present work we have studied daily data of prime stock exchanges of these E7 countries in order to study their scaling behaviours. Here we have used Finite Variance Scaling Method which is a form of scaling in order to find the corresponding Hurst Exponents. Hurst exponent is a measurement of the trend of the time series. It determines whether a time series is persistent (long memory process) or anti-persistent (short memory process) or random. Interestingly it is seen that some stock exchange data are persistent and some are anti-persistent. We have also studied the autocorrelation coefficients with different lags for all the present indices and study reveals that some of the indices are governed by autoregressive method, some of them by moving average method and some have mixed influence of both these two methods.

Trend Analysis of Share Prices on the Bombay Stock Exchange

2011

The oil and gas sector is one of the booming sectors in the Indian economy. This study aims at testing whether all the companies of a particular sector follow the same pattern in a given period of time. Behavioural studies have been a topic of controversy for long time. In general, two types of analysis are used to ascertain the price behaviour of the shares; viz; technical analysis and fundamental analysis. In this study, we have concentrated over the technical analysis. Our results explicated that a certain group of companies from a particular industry follows a similar pattern when it calls for the price changing behaviour of its shares in the stock market.

Persistence and Long Range Dependence in Indian Stock Market Returns

The Indian Stock Market is made up of participants from tick traders to long-term investors. Each participant having different investment horizons trade simultaneously in the market. This paper finds evidences of long memory in the returns from the data collected from Indian Bombay Stock Exchange. Fractal Market Hypothesis (FMH) explores the application of chaos theory and fractals to finance. The main idea of the fractal model is that the investors may not directly react to information. Instead, the investors may normally react with delay. The standard complement of statistical techniques used to identify predictable market structure, is capable of identifying regular periodic cycles. The Indian stock market has a high degree of persistence.

Stationarity of Stock Return Series in Indian Capital Market

European Journal of Scientific Research

Econometric models used in finance and commodity markets typically require the assumption that the data are stationary. Thus, the issue of stationarity has been studied at some length by economists and statisticians in the past decade. The stationarity is an essential property to define a time series process. A process is said to be covariancestationary or weak stationary, if its first and second moments are time invariant. A stationary process has the property to be mean reverting, i.e., it will fluctuate around its mean. Stationarity implies that no trend is observed in the time series. Stationary time series has wide applications in financial economics such as volatility modelling, testing market efficiency, cointegration and causality analysis. Thus, this paper attempts to measure the stationarity of stock return series in Indian capital market. The most wellknown stationarity tests, viz., the correlogram and unit root tests have been performed on the daily stock return series from Indian capital market over a period from January 1991 to August 2009 so as to include the periods of Asian Crisis of 1997, dot-com bust of 2001 and global financial crisis of 2008. The tests suggest the evidence of level stationarity of stock return series in Indian capital market over the sample period.

Scaling and Correlation in Financial Time Series

We discuss the results of three recent phenomenological studies focussed on understanding the distinctive statistical properties of ÿnancial time series -(i) The probability distribution of stock price uctuations: Stock price uctuations occur in all magnitudes, in analogy to earthquakesfrom tiny uctuations to very drastic events, such as the crash of 19 October 1987, sometimes referred to as "Black Monday". The distribution of price uctuations decays with a power-law tail well outside the LÃ evy stable regime and describes uctuations that di er by as much as 8 orders of magnitude. In addition, this distribution preserves its functional form for uctuations on time scales that di er by 3 orders of magnitude, from 1 min up to approximately 10 days. (ii) Correlations in ÿnancial time series: While price uctuations themselves have rapidly decaying correlations, the magnitude of uctuations measured by either the absolute value or the square of the price uctuations has correlations that decay as a power-law, persisting for several months. (iii) Volatility and trading activity: We quantify the relation between trading activitymeasured by the number of transactions N t -and the price change G t for a given stock, over a time interval [t; t + t]. We ÿnd that N t displays long-range power-law correlations in time, which leads to the interpretation that the long-range correlations previously found for |G t | are connected to those of N t .

Persistence characteristics of the Chinese stock markets

International Review of Financial Analysis, 2008

This paper identifies such fundamental characteristics as the lack of ergodicity, stationarity, and independence, and it identifies the degree of initial persistence of the Chinese stock markets when they were more regulated. The index series are from the Shanghai (SHI) stock market and Shenzhen A-shares (SZI) and B-shares (SZBI) stock markets, before and after the various deregulations and reregulations. Accurate and complete signal processing methods are applied to the complete series and to their sub-periods. The evidence of lack of stationarity and ergodicity can be ascribed to two causes: (1) the initial interventions in these stock markets by the Chinese government by imposing various daily price change limits, and (2) the changing trading styles in the course of the development of these emerging stock markets, after the Chinese government left these equity markets to develop by themselves. By computing the markets' monofractal Hurst exponents (and its accuracy range with a new statistic), using wavelet multiresolution analysis (MRA), we identify the markets' subsequent degrees of persistence. The empirical evidence shows that SHI, SZI, and SZBI are moderately persistent with Hurst exponents slightly greater than the Fickian 0.5 of the Geometric Brownian Motion. It also shows that these stock markets were considerably more persistent before the deregulations, but that they now move much more like geometric Brownian motions, i.e., efficiently. Our results also show that the Chinese stock markets are gradually and properly integrating into one Chinese stock market. Our results are consistent with similar empirical findings from Latin American, European, and other Asian emerging financial markets.