“…Between 2003 and late 2008, the correlations estimated by the expanded Kalman Filter and rolling windows often are negative. These negative correlations are consistent with the negative relation found by previous studies (Ferson and Harvey, 1995;Kaneko and Lee, 1995;Jones and Kaul, 1996;Sandorsky, 1999;De Roon et al, 2000;Ciner, 2001;Kilian and Park, 2007;Miller and Ratti, 2009 From 2009 through the end of the sample period in August 2011, all models indicate positive correlations between WTI and SP500, which are consistent with more recent results (Chen et al, 1986;El-Sharif et al, 2005;Narayan and Narayan, 2010;Lee and Chiou, 2011;Arouri and Rault, 2012;Büyükşahin and Robe, 2011;Tang and Xiong, 2012). This result is confirmed by results from the Kalman Filter that starts in 2006 (Fig.…”