APPLICATION OF ASYMMETRIC-GARCH TYPE MODELS TO THE KENYAN EXCHANGE RATE AND BALANCE OF PAYMENTS OF TIME SERIES DATA

Abstract

The critical concern of financial market investors is uncertainty of the returns. The symmetric-GARCH type models can capture volatility and leptokurtosis. However, they do not capture leverage effects, volatility clustering, and the thick tail nature of financial time series. The primary objective of this study was to apply the asymmetric-GARCH type models to Kenyan exchange and balance of payments of time series data to overcome the shortcomings of symmetric-GARCH type models. Secondary objectives included fitting asymmetric-GARCH type models to the Kenyan exchange rate and Balance of payments data, identifying the best asymmetric-GARCH type model(s) that best fit(s) the Kenyan exchange rate and Balance of payments data and forecasting the Kenyan exchange rate and Balance of payments data trends using the best asymmetric-GARCH type model. The study compared five asymmetric Conditional Heteroskedasticity class of models: IGARCH, TGARCH, APARCH, GJR-GARCH, and EGARCH. Monthly secondary data on the exchange rate from January 1993 to June 2021 and Balance of payments from August 1998 to June 2021 were obtained from the Central Bank of Kenya website. Asymmetric GARCH models were fitted to the stationary log-differenced data based on the functions in the RUGARCH package in R. The best fit model is determined based on minimum value of Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC). The optimal variance equation for the exchange rates data was APARCH (1,1) - ARMA (3,0) model with a skewed normal distribution (AIC = -4.6871, BIC = -4.5860) since it accounts for leverage and the Taylor effect. The optimal variance equation for the Balance of payment data was ARMA (1,1) - IGARCH (1,1) model with a skewed normal distribution (AIC = -0.14475, BIC = -0.07882) due to absence of (persistent) volatility clustering in the series. Volatility clustering was present in exchange rate data. Both series did not show evidence of leverage effect. Estimated Kenya’s exchange rate volatility narrows over time, indicating sustained exchange rate stability. While the balance of payment volatility has narrowed over time, the balance of payment deficit keeps widening. Thus, the government should take measures to ensure that it maintains it competitiveness in the global market to attract foreign direct investment and promote exports of goods and services.