作者: John T. Barkoulas , Christopher F. Baum , Nickolaos G. Travlos
DOI: 10.2139/SSRN.33672
关键词: Capital market 、 Long memory 、 Linear model 、 Economics 、 Financial economics 、 Stock (geology) 、 Stock market bubble 、 Stock market 、 Spectral regression
摘要: We test for stochastic long memory in the Greek stock market, an emerging capital market. The fractional differencing parameter is estimated using spectral regression method. Contrary to findings major markets, significant and robust evidence of positive long-term persistence found As compared benchmark linear models, models provide improved out-of-sample forecasting accuracy returns series over longer horizons.