Results Directory UMM :Data Elmu:jurnal:E:Energy Economics:Vol22.Issue6.2000:

G.E. Nasr et al. r Energy Economics 22 2000 627]640 633 residuals from the cointegration regression are used in the second stage as Ž . estimates of the true disequilibrium errors in an error correction model ECM . The ECM models the short-run dynamics within the framework of the long-term stable relationship established by the cointegration between variables. The ECM is estimated using the first-order lag errors from the cointegration model with appropriate lags on the different variables as follows: k l m Ž . DC s D q D DC q D DTI q D D DD q D u q e 7 Ý Ý Ý t o l i ty 1 2 i tyi 3 i tyi 4 tyi t is 1 is is Where D is the first-difference operator. The coefficient of the error, D , 4 represents speed of adjustment toward the long-run equilibrium.

4. Results

4.1. The 1993]1994 period Table 1 shows the estimated results at the 5 significance level for this period. The static model explains 40 of the variation in electricity consumption. The Ž . Durbin]Watson DW statistic is in the inconclusive region, at the 1 significance level, in testing for correlation of the residuals. TI is significant while DD correlates negatively to consumption with a regression coefficient of y0.26, which is obviously the wrong expected sign. The partial adjustment model does not show any improvement over the static model explaining 46 in electricity demand. Coefficient on TI is significant at the 5 level, while DD again correlates negatively. The lagged consumption coeffi- cient is also insignificant. Further analysis of the models on the time span Table 1 a Regression analysis results for the 1993]1994 time span Coefficient Static model Partial adjustment model A 259.9 150.0 Ž . Ž . 6.5 2.26 Ž . B T1 0.35 0.30 1 Ž . Ž . 3.38 2.61 Ž . B DD y 0.26 y 0.22 2 Ž . Ž . y 2.31 y 2.06 Ž . B C ] 0.34 3 ty 1 Ž . 1.95 2 R 0.40 0.46 Ž . DW or h 1.39 Negative a Figures in parentheses are t-statistics. G.E. Nasr et al. r Energy Economics 22 2000 627]640 634 Table 2 a Regression analysis results for the 1995]1997 time span Ž . Coefficient Static model AR 1 model Partial adjustment model A 195.2 573.7 y 20.3 Ž . Ž . Ž . 2.56 2.87 y 0.51 Ž . B TI 0.43 0.13 0.15 1 Ž . Ž . Ž . 5.31 2.73 3.52 Ž . B DD y 0.022 0.37 0.11 2 Ž . Ž . Ž . y 0.50 2.21 0.67 Ž . B C ] ] 0.79 3 ty 1 Ž . 12.0 r ] 0.94 ] Ž . 14.24 2 R 0.43 0.89 0.89 DW or h 0.43 2.19 Negative DF y 2.82 y 6.38 y 6.24 Ž . ADF 1 y 2.68 y 3.91 y 3.82 a Figures in parentheses are t-statistics. 1993]1994 along cointegration and ECM models is deemed to be unnecessary because of these results. The results for this period are not surprising considering the state of power generation capacity in Lebanon during 1993]1994. A widespread rationing policy was implemented during the war period and overflowed into the post-war era, specifically, into the 1993]1994 period. This rationing policy was largely implemented and electricity was supplied for 11.75 h in 1993 and 11.5 h in Ž . 1994. The electrical energy demand forecasted by Electricite Du Liban 1996 for 1993]1994 is 6306 GW-h for the year 1993 and 6800 GW-h for the year 1994. EDL was only able to produce 67 of the energy demand for both years. The electrical energy consumption in this period is hence considered supply-driven. 4.2. The 1995]1997 period Table 2 shows the regression analysis results at the 5 significance level. The static model explains 43 of the variation in electricity demand. The null hypothe- sis of no serial correlation is rejected using the DW statistic. The first-order Ž . Ž . Ž . autoregressive model, AR 1 , shown in Eqs. 4 and 5 is used to correct for the Ž . serial correlation. The DW test for the AR 1 model indicates absence of autocor- Ž . relation. DF and ADF 1 tests of the residuals from this model indicate stationary Ž . residuals and integration of zero order, I 0 . The model explains 89 of the variation in electricity demand. All coefficients are significant at the 5 level including the first order autoregressive term, r. Furthermore, DD is found to positively correlate to consumption. The coefficients of TI and DD are 0.13 and 0.37, respectively. G.E. Nasr et al. r Energy Economics 22 2000 627]640 635 The partial adjustment model explains 89 of the variation in electricity demand. The null hypothesis of no serial correlation cannot be rejected given the Ž . value of the Durbin h test. The DF and ADF 1 tests on the residuals indicate Ž . stationarity and integration of zero order, I 0 . All coefficients are significant at the 5 level except for DD. The coefficients of TI and DD are 0.15 and 0.11, respectively. The results indicate a major improvement over the 1993]1994 period. Once the Ž . autocorrelation of the residuals were accounted for, in the AR 1 model, all coefficients become significant at the 5 significance level with the right expected sign. The year 1995 represents a transition period for electricity production. Rationing hours which attained 12 h a day in 1993]1994 were significantly decreased during this year to 6.5 h a day. The results agree with many studies Ž found in the literature indicating the significance and impact of GPD Dincer and . Ž . Dost, 1997 and DD Al-Zayer and Al-Ibrahim, 1996 though considered sepa- rately, on electricity consumption. Specifically, the results indicate that an increase in GDP and DD implicates an increase in electrical energy consumption. 4.3. The 1996]1997 period In spite of the rationing hours that existed in 1995, analysis results of the 1995]1997 time period are found to be satisfactory. However, separate analysis for the 1996]1997 time period is performed since rationing was virtually non-existent for that period. Table 3 shows regression analysis results at the 5 significance level. The DW statistic for the static model indicates serial correlation of the residuals. The model R 2 is 0.13 and all determinants are insignificant at the 5 level. TI and DD coefficients are determined to be 0.22 and 0.39, respectively. The first order autoregressive model is also utilized to correct for serial correlation of the residuals. The model explains 54 of the variation in electricity demand. Again, all coefficients are significant at the 5 level including the first order autoregressive term, r. Furthermore, DD exhibits positive correlation to consump- tion. The performance of the partial adjustment model for this period appear to be as Ž . good as the AR 1 model. All coefficients are found to be significant at the 5 level except for DD. The model explains 46 of the variation in electricity demand. The null hypothesis of no serial correlation is not rejected using the Ž . Durbin h test. Again, the DF and ADF 1 tests indicate stationarity and integration Ž . of zero order, I 0 , of the residuals. TI and DD coefficients are 0.25 and 0.27, respectively. As rationing hours were virtually non-existent, starting 1996, in most of the country, the electrical energy imbalance of consumption and production was eliminated and electricity consumption started to be demand-driven.

5. Cointegration and error correction models