Search

We investigate the dynamic volatility connectedness of regional stocks, gold, Bitcoin, oil, and uncertainty index related to infectious diseases for the period from January 2014 to June 2022. We investigate the connectivity during Ebola & MERS periods, the normal period, the COVID-19 period and the full sample period. We find that the regional stock indices of the US, Europe, Africa and Latin America are net volatility transmitters whereas regional indices of Asia Pacific, Middle East and North Africa, and other assets like gold, oil and Bitcoin are net volatility recipients throughout the sample periods. By employing the TVP-VAR-based dynamic connectedness approach, we find the temporal evolution of system-wide total connectedness and pair-wise connectedness of financial assets to exhibit higher intensity of volatility spillover during the COVID-19 pandemic as compared to other sub-sample periods. We further observe, based on quantile connectedness approach, that the degree of dynamic connectedness is strong and significant across all the quantile spectrums only during the COVID-19 period. We observe that the safe haven characteristics of assets like gold, oil and Bitcoin diminish during the COVID-19 period due to strong dynamic connectedness with regional stock indices. Our findings have implications for policymakers, investors and portfolio managers in better risk management during periods of health epidemics and pandemics. [ABSTRACT FROM AUTHOR]

This research investigates the effectiveness of various machine learning models, including Random Forest, Neural Networks, Adaboost, Discriminant Analysis, Logit Model, Support Vectors, and Kernel Factory. The study aims to forecast fluctuations in the ASEAN-5 stock index prices within an eleven-year period. The study provides useful information about how well machine learning techniques can predict changes in the stock market, with potential implications for both academic researchers and market participants. The findings imply that Adaboost consistently outperforms all others in predicting price changes accurately. This shows that machine learning algorithms are capable of accurately forecasting the movement of the ASEAN-5 stock index values. This study contributes to the growing body of research on the use of machine learning techniques in finance and provides investors with information to make informed decisions about investments in the ASEAN-5 region, ultimately leading to increased returns and improved portfolio performance. [ABSTRACT FROM AUTHOR]

In this paper, we study the power of moment‐based normality tests which include Jarque Bera (JB) test and D′Agostino and Pearson (DP) omnibus tests. Power comparison were obtained via Monte Carlo simulation of sample data generated from four alternative distributions like Uniform, Logistic, Student t and Gamma distribution. Our simulation results show that for Uniform distribution, DP test has better power compared to JB test. For Logistic, Student t and Gamma distributions, we find JB normality test to be powerful compared to DP test. We further apply the moment‐based normality tests empirically on the Indian stock market indices (NSE Nifty 50 and BSE Sensex) for different frequencies (daily, weekly, monthly and quarterly) during the period from 2010 to 2020. We find that daily returns of Indian stock indices are non‐normal whereas weekly, monthly and quarterly returns are normally distributed. [ABSTRACT FROM AUTHOR]

Shaik and Maheswaran (2018) proposed the Expected Lifetime Range (ELR) ratio based on high minus low price (range) series to detect mean reversion. This paper extends this test statistic and proposes a set of test statistics—Expected Lifetime Surplus (ELSp) and Expected Lifetime Shortfall (ELSf) ratios—which are based on high and low price series respectively. These test statistics help in precisely detecting whether the source of market inefficiency is the high or the low price series. The paper empirically tests the three test statistics on the BRICS stock market indices. The sample period is divided into pre and post subprime crisis data sets. It is found that the BRICS stock market indices show mean reversion from 2001 to 2018. While in the pre subprime crisis period the indices followed random walk, after the subprime crisis the BRICS stock markets show mean reversion behavior. The source of this mean reversion are the high prices which have become more predictable after the subprime crisis. [ABSTRACT FROM AUTHOR]

In this paper, we study the performance of the Artificial Neural Networks (ANNs) and GARCH models to predict the volatility of the Indian stock market indices namely, NIFTY 50, NIFTY Bank and NIFTY FMCG. We have used the GARCH (1,1) and Recurrent Neural Network, a type of neural network which is widely used for predicting time series data. The purpose of the study is to investigate if the Artificial Neural Networks perform better than the traditional GARCH (1,1) model. An out of sample testing methodology is applied to the most recent 20 percent of the observations for all the three indices. We have used Root Means Squared Error (RMSE) and Mean Absolute Error (MAE) as metrics to evaluate the volatility predicting performances of the models. The results show no clear evidence of ANN model performing better than GARCH model for any of the three indices. ANNs may prove to be better indicators in periods with low volatility while its performance deteriorated in periods with high volatility. [ABSTRACT FROM AUTHOR]