Modelling the time‐varying volatility of equities returns in Kenya

Abstract

PurposeThe paper seeks to investigate the relationship between stock volatility and returns in the Nairobi Stock Exchange, Kenya. It uses daily returns data over the period January 2006 to April 2009.Design/methodology/approachEmpirical analysis is based on quantitative analysis with emphasis on descriptive statistics, and advanced econometrics models which are well suited to capture the time‐varying volatility. The models utilised in this study fall into the family of generalised autoregressive conditional heteroscedasticity models.FindingsThe main findings of the paper are as follows: the equities returns are symmetric but leptokurtic and thus not normally distributed; volatility of returns is highly persistent; the leverage effects are not significant; and the impact of news on volatility is not significantly asymmetric.Practical implicationsThe findings of this paper will aid policy makers, policy analysts, investors, and academics to gain in‐depth understanding of dynamics of the equities returns in Kenya particularly, with regard to leverage and impact of news.Originality/valueThe paper was conducted at a time when the volatility of the equity market returns in the global stock markets in general and Kenya in particular was high on account of the global financial crisis and the aftermath of the post‐election violence in Kenya. Given that excess volatility in the stock market undermines the reliability of stock market prices as a signal to the true value of the firm, the findings of this paper will provide useful insights in the assessment of portfolio allocation and investment decisions in Kenya.

Modeling volatility on the Karachi Stock Exchange, Pakistan

“…If γ = 0 then it shows no asymmetry and the model transforms to the standard GARCH model. If γ > 0 and is significant, it reflects the presence of a leverage effect[26] (Nyamongo and Misati, 2010). The coefficient β 1 reflects a clustering effect in volatility, and a persistence in volatility regarding the shock is reflected by α 1 + β 1 + γ /2 (Kalu and Friday, 2012)[27].…”

Islamic Calendar Anomalies: Evidence from Pakistan

“…To test the calendar anomalies on share returns and volatility for the Islamic months, GARCH model is used to find the presence of volatility on the KSE-100 index Nyamongo & Misati, 2010;Halari et al, 2015). Daily data of KSE-100 Index is used from November 2 nd 1991 to June 19 th 2014 i.e., 24…”

Volatility Model Choice for Sub-Saharan Frontier Equity Markets - A Markov Regime Switching Bayesian Approach

“…Single regime GARCH models are the principal tools of choice for volatility modeling in the frontier markets in sub-Saharan Africa. Some recent papers are Carsamer (2016), Uyaebo, Atoi and Usman (2015), Chinzara and Slyper (2013), Esman Nyamongo and Misati (2010), Adjasi (2009), among others.…”