You do a study of stock market returns (for the S&P 500). You are particularly interested in days when the market drops by more than 2%, yet the VIX (CBOE Volatility Index) does not increase - as the leverage effect would predict. You suspect that this is a bullish sign, and as a consequence the next day the market should therefore go up. A study of daily market returns since 2003 shows that this is true, and statistically significant. Then this would be evidence against the semi-strong form Efficient Market Hypothesis