Constantine Asaturov

The paper examines dynamic systematic risk nature of the Indian companies in the frame of the market model. The closing weekly prices of 89 Indian stocks and BSE 100 index as the market index during the period from January 2000 to December 2013 are analyzed with rolling OLS, multivariate GARCH models, semiparametric regression and a Kalman Filter. According to the results for the analyzed period, in 44 out of 89 cases Kalman Filter is the best model, while semiparametric regressions – in the other 45 cases. As for the forecasted period, for 41 out of 89 stocks multivariate GARCH-models surprisingly outperform both semiparametric models (33 out of 89) and a Kalman Filter technique (15 out of 89). Moreover, analysis of the betas dynamic shows that for 5% signifi cance level 59 and 62 out of 89 time-varying betas processes are non-stationary according to ADF and Philips–Perron tests respectively and the only one of the processes is stationary according to KPSS test.