Efficiency Evaluation When Modelling Nairobi Security Exchange Data Using Bilinear and Bilinear-Garch (Bl-Garch) Models
ADOLPHUS WAGALA, ALI S. ISLAM, DANKIT K. NASSIUMA

Abstract
In this paper, the weekly returns of the Nairobi Securities Market (NSE) are modelled using bilinear models and the bilinear-GARCH models so as to determine the most efficient and adequate model for forecasting of the Nairobi Equity market. The data used was obtained from the Nairobi Stock Exchange (NSE) for the period between 3rd June 1996 to 31st 30th October 2011for the company share prices while for the NSE 20-share index was for period between 2nd March 1998 to 30th October 2011.The share prices for three companies; Bamburi Cement, National Bank of Kenya and Kenya Airways which were at random from each of the three main sectors as categorized in the Nairobi Stock Exchange were used. The results indicate that the combination of bilinear-GARCH model is more adequate and efficient in modelling the weekly returns of the Nairobi Securities Exchange.

Full Text: PDF