Le Système SAS 19:49 Wednesday, March 19, 2008 23 The ARIMA Procedure Name of Variable = X Period(s) of Differencing 12 Mean of Working Series 0.434783 Standard Deviation 138.0166 Number of Observations 23 Observation(s) eliminated by differencing 12 Autocorrelations Lag Covariance Correlation -1 9 8 7 6 5 4 3 2 1 0 1 2 3 4 5 6 7 8 9 1 Std Error 0 19048.594 1.00000 | |********************| 0 1 -2728.917 -.14326 | . ***| . | 0.208514 2 2029.301 0.10653 | . |** . | 0.212751 3 -410.645 -.02156 | . | . | 0.215058 4 312.549 0.01641 | . | . | 0.215152 5 -603.230 -.03167 | . *| . | 0.215206 "." marks two standard errors Inverse Autocorrelations Lag Correlation -1 9 8 7 6 5 4 3 2 1 0 1 2 3 4 5 6 7 8 9 1 1 0.11713 | . |** . | 2 -0.08714 | . **| . | 3 -0.01063 | . | . | 4 0.00234 | . | . | 5 0.02759 | . |* . | Partial Autocorrelations Lag Correlation -1 9 8 7 6 5 4 3 2 1 0 1 2 3 4 5 6 7 8 9 1 1 -0.14326 | . ***| . | 2 0.08781 | . |** . | 3 0.00509 | . | . | 4 0.00503 | . | . | 5 -0.02831 | . *| . | Le Système SAS 19:49 Wednesday, March 19, 2008 24 The ARIMA Procedure Augmented Dickey-Fuller Unit Root Tests Type Retards Rho Pr < Rho Tau Pr < Tau F Pr > F Zero Mean 0 -25.4945 <.0001 -5.11 <.0001 1 -19.7741 0.0003 -2.94 0.0053 2 -20.2363 0.0002 -2.68 0.0101 3 -19.0463 0.0003 -2.06 0.0402 4 -29.0440 <.0001 -2.03 0.0428 5 -43.7369 <.0001 -1.69 0.0835 6 -31.3836 <.0001 -1.22 0.1913 Single Mean 0 -25.5060 0.0001 -4.97 0.0007 12.41 0.0010 1 -19.7016 0.0019 -2.85 0.0687 4.10 0.1043 2 -19.5083 0.0018 -2.57 0.1156 3.57 0.2273 3 -17.9763 0.0033 -1.98 0.2917 2.14 0.5572 4 -25.6882 <.0001 -1.99 0.2878 2.27 0.5272 5 -36.4828 <.0001 -1.70 0.4131 1.65 0.6705 6 -27.0824 <.0001 -1.22 0.6391 0.82 0.8606 Trend 0 -28.5924 0.0002 -5.86 0.0005 17.32 0.0010 1 -34.2670 <.0001 -3.70 0.0456 6.85 0.0648 2 -52.5450 <.0001 -3.01 0.1529 4.67 0.3164 3 565.8800 0.9999 -2.61 0.2817 3.42 0.5347 4 30.0856 0.9999 -2.52 0.3175 3.32 0.5517 5 12.4940 0.9999 -2.54 0.3070 3.33 0.5508 6 7.2432 0.9999 -3.07 0.1460 4.71 0.3103 Conditional Least Squares Estimation Erreur Pr. Paramètre Estimation standard Valeur du test t Approx. > |t| Retard MU -0.81541 25.87048 -0.03 0.9752 0 AR1,1 -0.15931 0.22747 -0.70 0.4914 1 Constant Estimate -0.94532 Variance Estimate 20386.59 Std Error Estimate 142.7816 AIC 295.3994 SBC 297.6704 Number of Residuals 23 * AIC and SBC do not include log determinant. Le Système SAS 19:49 Wednesday, March 19, 2008 25 The ARIMA Procedure Correlations of Parameter Estimates Parameter MU AR1,1 MU 1.000 0.059 AR1,1 0.059 1.000 Autocorrelation Check of Residuals To Chi- Pr > Lag Square DF Khi2 --------------------Auto-corrélations------------------- 6 0.31 5 0.9975 0.015 0.092 -0.010 0.007 -0.030 -0.033 12 6.84 11 0.8121 0.003 0.256 0.045 -0.076 0.067 -0.257 18 12.73 17 0.7544 -0.135 -0.183 -0.048 0.005 0.025 -0.147 Model for variable X Estimated Mean -0.81541 Period(s) of Differencing 12 Autoregressive Factors Factor 1: 1 + 0.15931 B**(1)