Spurious Regressions The problem with nonstationary or trended data is that (OLS) regression procedures can easily lead to incorrect conclusions . . In these cases that the regression results have very high value of R2 (sometimes even higher than 0.95) and very high values of t-ratios (sometimes even higher than 4), while the variables used in the analysis have no real interrelationships. (2007Asteriou)
Example1(Spuriouse Regression) Yt = -22.024 – 0.50Xt Se 0.601 0.065 t-statistic -36.49 -7.81 Prob. 0.0000 0.0000 R-Squared 0.109 Durbin Watson 0.014 F-statistic 60.974 Prob(F-statistic) 0.0000