Time-varying conditional dependence in Nairobi Stock Market

Abstract

This study explores the dependence between the shares traded at the Nairobi stock Exchange and the prices for which the various companies' shares were selling. Using simulated time-series of financial asset returns, the results show that market dependence is not generally conditional on volatility regimes and that a bias in dependence measures occurs only for particular assumptions about the time-series dynamics. Since real world data may often not be characterized by homoskedasticity, a correction of estimated unconditional correlations during market crises may not always be needed. Consequently, if the return data generating process is invariant but displays conditional heteroskedasticity, a conditioning bias exists that cannot be distinguished from a fundamental change in market dependence. While the marginal behaviour of each stock index is modelled by an asymmetric Student-t distribution, the nature of the dependence is captured through a copula representation. The results also confirm the already documented time-varying pattern of the dependence structure.