Authors:Hsin-Ning Su, Carey Ming-Li Chen and Pei-Chun Lee
suggested for future study in order to obtain the best model with minimized error in regression modeling, (2) the use of logisticmodel might not be perfect due to uneven numbers of litigated-patents and non-litigated patents, a revised or more advanced
Authors:X. H. Fan, H. J. He, J. Wang, C. Y. Xu and K. v. Gadow
The geographical patterns of tree species richness in forest communities have been studied widely, but little is known about the geographical variation of the estimated species richness and minimum areas using species-area curves. A differential technique based on the species-area relationships (SAR) was developed for estimating the minimum area (Amin) capturing 60- 80% of the species in each plot, which is an important characteristic of a forest community. The relationship between estimated species richness (ESR) from the SAR and the corresponding minimum area is described by the linear model ESR = 0.0051×Amin (R2 = 0.98, p < 0.0001). Both the ESR and the minimum area exhibit similar geographical variations with a significant increase along altitudinal and a decrease along latitudinal gradients. The spatial variations of the ESR were partitioned into three geographical components and their combined effects. Altitude accounted for 40% and 45% of the total variation in the ESR and the minimum area, respectively. While latitude accounted for 69% and 61% of the total variation in the ESR and the minimum area, respectively. Thus, latitude is the main determinant which influences the geographical variation of the ESR. As far as we know, this study presents the first report of the geographical patterns of the minimum area in temperate forests.
Establishment of an effective early warning system can make the company operators make relevant decisions as soon as possible when finding the crisis, improve the operating results and financial condition of enterprise, and can also make investors avoid or reduce investment losses. This paper applies the partial least-squares logistic regression model for the analysis on early warning of enterprise financial distress in consideration of quite sensitive characteristics of common logistic model for the multicollinearity. The data of real estate industry listed companies in China are used to compare and analyze the early warning of financial distress by using the logistic model and the partial least-squares logistic model, respectively. The study results show that compared with the common logistic regression model, the applicability of partial least-squares logistic model is stronger due to its eliminating multicollinearity problem among various early warning indicators.
Authors:B. Gupta, Praveen Sharma and C. Karisiddappa
The paper discusses the application of three well known diffusion models and their modified versions to the growth of publication
data in four selected fields of S&T. It is observed that all the three models in their modified versions generally improve
their performance in terms of parameter values, fit statistics, and graphical fit to the data. The most appropriate model
is generally seen to be the modified exponential-logistic model.
The paper deals with the nature of growth models currently used in the literature for modeling the growth of publications.
It introduces briefly three growth models and explores the applicability of these models in the growth of world and Indian
physics literature. The analysis suggests that the growth of Indian physics literature follows a logistic model, while the
growth of world physics literature is explained by a combination of logistic and power models. The criteria for selection
of growth models based on the new growth rate functions suggested by Egghe and Ravichandra Rao are given. The methodology
suggested by Egghe and Ravichandra Rao is shown to work satisfactorily, except for longer time series growth data, when we
may have to restore to data splitting approach, if suggested by the plots of new growth rate functions. This approach helped
us to use a combination of two growth models instead of one, to explain the growth of world physics literature.
This paper is the third in a series on the flows of influence at the interface between geoscience research and the exploration for and mining of nuclear fuels. It deals with the application of signal processing methods to research and industry indicators, with emphasis on time and frequency domain correlations and lags, and on growth modelling of the indicators using the special and general logistic models. The findings include the following: there was a strong interchange across the science-industry interface; quantitative methods can establish the degree of correlation and the time periods in which these correlations mainly reside; also the timing of decisions to initiate exploration and research can be specified in this case. A strategy of applying quantitative methods, history of science, and periodic analyses of the state of the industry to studies of science policy is suggested by this research.
Authors:Angel-Alex Hăisan, Zizi Goschin and Mihai Avornicului
Mass migration was, is, and will always be an important topic of discussion regardless of whether it is economically, socially, or politically motivated. This is certainly a matter of great concern for Romania, currently Europe’s largest sender of migrants to Western Europe. Considering that the educational system should be of the uttermost priority, we addressed the issue of emigration propensity among Romanian teachers making use of data from our own nationwide survey. Bivariate logistic models were employed to identify the main factors behind the emigration decisions of pre-university teachers. Aiming to enrich the narrow economic perspective, we adopted a novelty approach by focusing on an overlooked determinant in emigration research studies, namely ethnicity in relation to nationality. Among Romania’s minorities, Hungarians are the most important ethnic group, accounting for 6.1% of the population, hence we explored their migration behaviour compared to Romanian ethnics. The results from the logistic regression models indicate significant differences regarding the factors that trigger the intention to initiate the emigration process for our subjects, based on their ethnicity. We found that teachers of Hungarian ethnicity display 50.6% less propensity to emigrate compared to the ones of Romanian ethnicity and we were able to shape distinct emigration profiles for the two groups.