This paper aims to clarify which characteristics influence the number of urban park visitors. The study employs a residual analysis as a heuristic approach, which is a useful approach to choose explanatory variables effectively. In fact these characteristics are difficult to identify among numerous related variables, and a big residual value may involve the significant factor. The results reveal five major factors to have influences on the number of park visitors in concern: 1) population living in park's service distance; 2) volume of tall trees; 3) number of simple amusement equipment/facilities; 4) width of streets facing to a park; and 5) park elevation relative to surrounding road level. In addition, it was found that a block park has a service distance of 250 to 350 meters.
A metric multidimensional unfolding procedure is proposed to represent the rows (individuals) and columns (items) of a proximity data matrix as the points in a low-dimensional space. The procedure is based on a random effect model which allows us to avoid the problem of incidental parameters. In the model, the individual points are regarded as normally-distributed random variables, while the item points are regarded as fixed parameters. The probability density of the proximity data is derived from the assumption that the true proximity is a linear function of the distance from the individual point to the item point and the observed proximity is perturbed by the normally-distributed error. The marginal likelihood obtained by integrating out the random individual points is maximized using the EM algorithm with a generalized SMACOF algorithm. The proposed procedure is evaluated with a simulation study and is applied to a preference rating data.
This paper analyzed the present and future method for providing road traffic information, based on the poll that Metropolitan Expressway Public Corporation (here in after called as MEPC) had carried on in January 1997. More than 80% of the drivers who use road information media such as changeable message signs and roadiside radios said their effectiveness. But, 65% of drivers said they were dissatisfied not to get the information of the whole road network and required enhancing the media that can provide personal information such as service with internet and automatic responding telephones. However, the data suggests that new media are not expected to use effectively by only effort of MEPC, but it is valuable for those who are positive to obtain information and have the spirit of self-help.
Within the past decade, structural equation modeling (SEM) has been a well known component of the methodological arsenal of the social sciences and behavioral sciences in Japan. This approach is being employed in an expanding range of substantive areas because of it includes many conventional statistical method such as the general linear model and factor analysis. This review paper is intended for researchers and students who want to study and use SEM or covariance structure analysis described in books and articles published previously.