Significance Test for Final Model 1

71 Table 17. Pseudo R-Square Statistics 1 st Scenario Pseudo R-Square .914 .919 .456 Cox and Snell Nagelkerke McFadden The pseudo r-squared statistics are designed to have similar properties to the true r-squared statistic, which measures the variability in the dependent variable that is explained by a linear regression model. Larger pseudo r-squared statistics indicate that more of the variation is explained by the model, to a maximum of 1. There were three approaches of pseudo r-squared statistics which have been done in this research which have been proposed by Cox and Snell, Nagelkerke, and McFadden. Based on the computation, pseudo r-squared statistics, either Cox and Snell or Nagelkerke, indicate that the variability of the land use change in Siak District as dependent variable can be explained more than 0.91, whereas according to McFadden, it is only 0.456. In other word, according to Cox and Snell and Nagelkerke, more than 91 of the variability of land use change in Siak District can be explained by the final model developed, and McFadden indicate only 45.6 of the variability can be explained by the model. However, in general the pseudo r-squared statistics that have been produced indicates that most of variability in land use change which happen in Siak District could be explained by the final model. The two tests for final model which have been conducted, likelihood ratio test for the final model and pseudo r-squared, indicate that the final model of land use change in Siak District which has been developed by using MLR model is a good model that can explain most of the variability of land use change in the research site. The significant variables that have been determined can be concluded as general driving factors which drive the land use transitions in Siak District. Furthermore, these research findings, which have been interpreted from the statistical computation, should be spatially compared to the actual condition in order to validate the performance of the MLR model when the model is applied in spatial manner. 72

1.4.2.3 Parameter Estimates 1

st Scenario The MLR model analysis has been done by using land use category 1 as reference category which is a transition from Forest land to Forest land FF. The table of the parameters coefficients for the final model of land use change in Siak District which can be seen in Appendix 3 shows that every land use transitions categories are contributed by all significant variablesparameters which have been determined; there are 24 parameters and 1 interceptconstant in each land use transition. The coefficients of the parameters β vary from one land use transition to other land use transition. The parameters with significant negative coefficients decrease the likelihood of that response category dependent variable with respect to the reference category, whereas the parameters with positive coefficients increase the likelihood of that response category. These show that the parameters may affect the land use transitions in different contribution of effects. The natural environment has 6 significant parameters which contribute in land use change in Siak District. From all significant parameters in natural environment, only distance from Forest land has significant positive coefficients which contribute the increasing of the likelihood of all land use transitions as response categories. The increasing distance from Forest land will increase the likelihood of land uses to transform into other land uses. The distance from River seems to have the same contribution as distance from Forestland, but the coefficients of its parameter are very small which are close to 0.000. Furthermore, the increasing distance from Cropland, Grassland, Wetlands, and Other lands will increase the likelihood of some land use transitions, and also will decrease the likelihood of the rest land use transitions. For instance, the distance from Cropland will decrease the likelihood of land use transition FC 2, CF 6, CC 7, CG 8, CS 9, and CO 10, whereas it will increase the likelihood of the rest land use transitions. The distance from Grassland contributes negative effect to the likelihood of land use transition CS 9, OS 25, all land use transitions from Grassland GF, GC, GG, GS, GO, and all land use transitions from Settlements SF, SC, SG, SS, SO, along with the increasing of distance from Grassland. The distance from Wetland will increase the likelihood of most land use transitions along with the increasing of its distance, and also decrease the likelihood of land 73 use transition WW 16, and OO 26. The decreasing distance from Other lands will increase the likelihood of land use transition GO 15, all land use transitions from Settlement, and all land use transition from Other lands. The human environment contributes 15 parameters on the land use change model of Siak District. Most of parameters in human environment have positive coefficients with value which are close to 0.000 for most land use transitions in Siak District, and only distance from road and population density have different coefficients characteristics. The distance from road is the parameter that contributes in decreasing the likelihood of most land use transitions, and only land use transition FS 4, CG 8, CS 9, CO 10, and GC 12 have positive coefficients which are close to 0.000. These mean that the increasing distance from road will decrease the likelihood of most land uses to transform into other land uses, and reversely the closer distance from road will increase its likelihood. The population density has positive coefficients which will contribute the increasing of the likelihood of all land use transitions in Siak District. The increasing population density will increase the likelihood of land use transitions which happen in Siak District. The policy contributes 3 parameters on the final model that are Forestry Spatial Plan at national level, Spatial Plan at province level, and Forestry and Crop Spatial Plan at district level. The Forestry Spatial Plan at national level contributes the effect to the likelihood of most land use transitions negatively, and only likelihood of land use transition WW 16, OG 24, OS 25, and OO 26 which will be increased because of the implementation of its spatial plan. In other word, the Forestry Spatial Plan at national level may drive the land use transitions happen in Siak District which prevent most of land uses to be transformed into other land uses, keep the Wetlands and Other lands in stable condition, and in the same time increase the utilization of bareland as the major land use in Other lands by replanting vegetation and developing the settlement area. The Spatial Plan at province level has little different effect to the likelihood of land use transitions rather than the Forestry Spatial at national level. The Spatial Plan at province level prevent most of land uses to be transformed into other land uses, keep the Grassland, Wetlands and Other lands in stable condition, and in the same