Stationary Test Data Processing

70 The requirement to reject the H is, H is rejected if the JB value is chi square table, or H is rejected if the probability of the Jarque –Bera is α 0.05. The result of JB test can be seen in the following figure: Figure 4.2 The Result of Jarque –Bera Test for Normality Based on the figure 4.2, the result of JB test shows that the value of Jarque –Bera is 358.45 that is more than chi square table, that is 89.γ9, and the probability of JB is 0.00, that is less than the α 0.05. thus, it can be concluded that the residuals is conceive of the normality problem. According to Wooldridge in Ariefianto 2012:148, one of the advantage of using the panel data is, it becomes robust toward the violation of the Gauss Markov assumption, which are: heteroscedasticity and normality. Since, this research is using the 5 10 15 20 25 -300 -200 -100 100 200 300 400 500 600 700 Series: Standardized Residuals Sample 2009 2013 Observations 70 Mean 1.14e-14 Median -22.61085 Maximum 694.1472 Minimum -253.3945 Std. Dev. 136.5552 Skewness 2.514476 Kurtosis 12.87978 Jarque-Bera 358.4595 Probability 0.000000 71 panel data analysis, thus it can be concluded that the residuals is robust from the normality problem. 2 Heteroscedasticity Test As mentioned in the chapter 3, one of the way to test the heteroscedasticity problem is using white heteroscedasticity test. In this research, the researcher is using gretl application to detect the heteroscedasticity problem. The assumption to reject the null hypothesis is: H is rejected if the p- value α 0.05. The result of white heteroscedasticity test can be seen in the following table: Table 4.11 The Result of White Heteroscedasticity Test Whites test for heteroskedasticity OLS, using 70 observations Dependent variable: uhat2 coefficient std. error t-ratio p-value -------------------------------------------------------------- const 83225.7 69221.9 1.202 0.2350 gdpgrowth -5809.09 8547.24 -0.6796 0.4999 inflation 15838.8 18355.5 0.8629 0.3924 unemployment -17444.6 10634.2 -1.640 0.1073 import -2008.52 1461.40 -1.374 0.1756 cab 8231.88 6920.08 1.190 0.2399 sq_gdpgrowth 126.429 690.376 0.1831 0.8555 X2_X3 -760.834 1420.90 -0.5355 0.5948 X2_X4 -166.497 991.457 -0.1679 0.8673 X2_X5 -16.3650 59.5365 -0.2749 0.7846 X2_X6 1399.39 753.605 1.857 0.0693 sq_inflation -576.417 610.114 -0.9448 0.3494 X3_X4 396.706 1629.28 0.2435 0.8086 X3_X5 41.9809 130.135 0.3226 0.7484 X3_X6 -1954.38 1021.74 -1.913 0.0616 sq_unemployme 130.098 280.936 0.4631 0.6454 X4_X5 330.567 120.936 2.733 0.0087 X4_X6 -1160.93 626.104 -1.854 0.0697 sq_import 3.14821 4.68264 0.6723 0.5045 X5_X6 -49.6438 65.8908 -0.7534 0.4548 sq_cab 141.950 276.939 0.5126 0.6106 Unadjusted R-squared = 0.435551 Test statistic: TR2 = 30.488563, with p-value = PChi-square20 30.488563 = 0.062315 Source: processed data 72 Based on white heteroscedasticity test that provided in the table 4.11, it is known that the p-value 0.062315 is higher than α 0.05, it means that the null hypothesis of homoscedastic can be accepted. Therefore, it can be concluded that the data in this research does not conceive heteroscedasticity. 3 Multicollinearity Test Multicollinearity test aimed to figure out whether there is a collinear relationship cross the independent variables. Multicollinearity problem led by the usage of two variables that have a derived relationship in one model. According to Nachrowi and Usman 2006, the strong multicollinearity has value 0.8. The result of multicollinearity test can be seen in the following table: Table 4.12 The Result of Multicollinearity Test GDP INF UNEMP IMP CAB GDP 1.000000 0.494156 -0.486683 0.056883 0.182503 INF 0.494156 1.000000 -0.254561 0.181292 -0.080442 UNEMP -0.486683 -0.254561 1.000000 -0.242006 -0.384453 IMP 0.056883 0.181292 -0.242006 1.000000 0.283485 CAB 0.182503 -0.080442 -0.384453 0.283485 1.000000 Source: processed data 73 Based on the multicollinearity test that provided in the table 4.12, it is known that the value of each variable GDP, INF, UNEMP, IMP, CAB toward the other variables is less than 0.8. Thus, it can concluded that there is no multicollinearity contained on GDP growth, inflation, unemployment, import, and current account balance variable. 4 Autocorrelation Test The aim of autocorrelation test is to detect the internal correlation among the groups of a series observation arrange in a series of place and time. According to Ariefianto 2012:30 the commonly uses testing method to test the autocorrelation Durbin- Watson test DW tests. If the result shows that 2 DW 4 – d u it can be concluded that there is no autocorrelation. The result of Durbin-Watson test can be seen in the following table: Table 4.13 The Result of Autocorrelation Test using Durbin-Watson Statistic DW count d u table value 4 – d u dL table value 4 – dL 1.747141 1.8025 2.1975 1.4326 2.5674 Source: data processed