In the present study the assumed hypothesis that there is a considerable degree of interdependence between the degree of urbanization and the development level of a transportation system has been examined in the case of 59 municipalities in Ehime prefecture. For this purpose, first, the degrees of urbanization, and the development levels of transportation systems, of the municipalities were quantified by way of a principal component analysis, to the results of which were then applied regression analysis and analysis of variance, respectively, so as to find out relationships between them and their significance. Finally, residuals, or differences between the observed and predicted values of the degrees of urbanization were calculated, the sources of which being then inquired into. The results of these analyses may be summarized as follows: 1. As a result of the principal components analysis applied to the 49 variables which represent regional characteristics, the urbanization degree factor is obtained as the primary factor that can explain 38.8 per cent of the total variance. This shows the significance of the degree of urbanization as the fundamental dimension for the regionality of the prefecture. 2. The principal components analysis of the 17 variables for the levels of transportation systems yields five principal components with eigenvalues over unity. Of these five the first factor referring to terminal facilities for transportation explains as much as 41.2 per cent of the total variance. From this it turns out that the development level of a transportation system can be estimated to a large extent by the terminal facilities factors. 3. Our conclusions based on the results of the regression analysis and analysis of variance are: (1) there is a significant interdependence between the degree of urbanization and the development level of a transportation system, and (2) the larger portion of the variation in degrees of urbanization can be estimated in most cases in terms of the terminal facilities of the municipalities. 4. An inspection of the residuals reveals that the samples consist of two major groups. Group I having high values with positive loadings and Group 11 having high values with negative loadings, the former of which is further composed of three subgroups. A, B and C. From a further examination of the residuals for the subgroups is derived our conclusion that they are closely related to the historical backgrounds and regional characteristics of each of the municipalities here considered.
抄録全体を表示