8885898E 公国 5g8 g彐88g &2 989582 ^+" 点 日 三豆器 四郾8于8 器当 足自当岩 2云云云E岩 z 9且三且三且三三ETABLE 2. Cointegrution Regressions Coefficients of Variable In Ml In MlA In M2 In Ml In MlA In M2 In Ml In MlA In M2 CONST In y In P In r, -1.04 0.407 0.856 - -2.41 0.784 0.440 - -5.55 1.080 0.953 - -2.12 0.575 0.855 -0.125 -2.64 0.821 0.439 -0.270 -6.35 1.204 0.952 -0.092 -0.28 0.283 1.010 - -2.44 0.790 0.433 - -5.23 1.028 1.018 - ln rd - - - - - - -0.300 0.014 -0.128 R2 DW DF ADF 0.99 0.03 1.95 -0.90 0.99 0.09 -1.85 -1.98 0.99 0.15 -1.95 -2.99 0.99 0.11 -0.54 -1.79 0.99 0.09 -1.92 -2.07 0.99 0.53 -4.21** -3.00 0.99 0.30 -2.18 -3.10 0.99 0.09 -1.86 -2.03 0.99 0.34 -3.32 -3.77** NOTES: The errors from the cointegration equations are recovered to perform the augmented Dickey-Fuller non-stationarity tests based on the following regression: 4 Dq = tk-, + 2 ‘~liDc,-i + p, , i=, where l , is the error from the cointegration equation, pt is a stationary random error, and the null hypothesis of non-stationarity is rejected when 6 is significantly negative. The Dickey-Fuller (DF) tests for non-stationarity delete the summation. R2 is the adjusted coefficient of determination, and DW is the Durbin-Watson statistic. *sign&cant at the 5% level. **significant at the 10% level