Are international stock returns predictable? An application of spectral shape tests corrected for heteroskedasticity

This paper uses spectral tests to examine whether international stock index returns are predictable using the history of the series. Unlike many other testing procedures, the spectral tests used in this paper are robust to distributional assumptions and the presence of time-varying volatility. We find little evidence to support predictability in most international stock markets, with a few exceptions. Canada's TSE 100, Italy's BIC, and the UK's FTSE 100 index returns do show a degree of predictability. The TSE 100 and BIC results are consistent with long-run mean reversion, while the FTSE 100 result is more consistent with short-run phenomena.