刺槐人工林经营质量动态监测模型

采用多元非线型回归模型建立了刺槐人工林林分平均直径、林分优势高、林分平均高、林分断面积、林分蓄积和林分经营密度的动态监测模型,所有模型的相对系统误差小于±2.8%,相对均方差小于4.9%。并根据生产实践需求,编制了刺槐人工林现实收获表,用于现实林经营质量的动态监测。

我国上市公司资本结构影响因素分析--基于钢铁行业上市公司的实证研究

公司资本结构是否合理直接影响到公司经营业绩和长远发展。运用多元回归分析法,对我国钢铁行业上市公司的资本结构的影响因素进行实证分析,结果表明:钢铁行业上市公司利息保障倍数以及股权结构与资本结构呈显著的正相关关系、钢铁行业上市公司非负债税盾以及成长性与资本结构呈显著的负相关关系等。

上市公司资本结构特征和影响因素分析

本文以钢铁行业上市公司为研究对象,对我国钢铁行业上市公司的资本结构特征和影响因素进行了实证分析,以期对钢铁行业上市公司选择合适的资本结构提供经验证据,为其理性成长作出启示。

电子行业上市公司资本结构影响因素的实证分析

公司资本结构是否合理直接影响到公司经营业绩和长远发展。本文以我国深沪两市的电子行业上市公司为研究对象,运用多元回归分析法,对我国电子行业上市公司的资本结构影响因素进行了实证分析。

广义岭型主相关估计的方差最优性

本文在回归系数的岭型主相关估计的基础上,提出了广义岭型主相关估计,进一步研究其在降维估计类中方差最优性。

“84办法”在特小流域洪峰流量计算中的应用

“84办法”是安徽省水利部门在中小流域（10～300 km2）洪峰流量计算中的常用方法,但在特小流域中（＜10km2）的应用较少.以安徽省马鞍山市雨山现代农业示范园内的防洪渠设计洪水分析计算为例,将“84办法”与特小流域中计算洪峰流量常用的两种方法即中国水科院1958年推理公式法和中国公路科学研究所经验公式法进行比较、分析与讨论,认为“84办法”在特小流域洪峰流量计算中的应用是合理可行的.

消费、投资与股票价格关系的实证研究

利用2003年第1季度到2015年第2季度的季度数据,建立多元线性回归模型来分析股票市场价格波动对居民消费和企业投资的影响。结果发现,股票价格波动与居民消费支出不相关,股票市场不存在消费效应。股票价格与企业投资正相关,股票市场存在一定的投资效应。

Diagnostics in generalized nonlinear models based on maximum L_q-likelihood estimation

In order to detect whether the data conforms to the given model, it is necessary to diagnose the data in the statistical way. The diagnostic problem in generalized nonlinear models based on the maximum Lq-likelihood estimation is considered. Three diagnostic statistics are used to detect whether the outliers exist in the data set. Simulation results show that when the sample size is small, the values of diagnostic statistics based on the maximum Lq-likelihood estimation are greater than the values based on the maximum likelihood estimation. As the sample size increases, the difference between the values of the diagnostic statistics based on two estimation methods diminishes gradually. It means that the outliers can be distinguished easier through the maximum Lq-likelihood method than those through the maximum likelihood estimation method.

A topographical model for precipitation pattern in the Tibetan Plateau

As the highest and most extensive plateau on earth, the Tibetan Plateau has strong thermo- dynamic effect, which not only affects regional climate around the plateau but precipitation patterns of scattered meteorological also temperature and itself. However, due to stations, its spatial precipitation pattern and, especially, the mechanism behind are poorly understood. The availability of spatially consistent satellite-derived precipitation data makes it possible to get accurate precipitation pattern in the plateau, which could help quantitatively explore the effect and mechanism of mass elevation effect on precipitation pattern. This paper made full use of TMPA 3B43 V7 monthly precipitation data to track the trajectory of precipitation and identified four routes （east, southeast, south, west directions） along which moisture-laden air masses move into the plateau. We made the assumption that precipitation pattern is the result interplay of these four moisture- laden air masses transportation routes against the distances from moisture sources and the topographic barriers along the routes. To do so, we developed a multivariate linear regression model with the spatial distribution of annual mean precipitation as the dependent variable and the topographical barriers to these four moisture sources as independent variables. The result shows that our model could explain about 7o% of spatial variation of mean annual precipitation pattern in the plateau; the regression analysis also shows that the southeast moisture source （the Bay of Bengal） contributes the most （32.56%） to the rainfall pattern of the plateau; the east and the south sources have nearly the same contribution, 23.59% and 23.48%, respectively; while the west source contributes the least, only 2o.37%. The findings of this study can greatly improve our understanding of mass elevation effect on spatial precipitation pattern.

Optimal timing of staged percutaneous coronary intervention in ST-segment elevation myocardial infarction patients with multivessel disease

Background Studies have shown that staged percutaneous coronary intervention （PCI） for non-culprit lesions is beneficial for prog- nosis of ST-segment elevation myocardial infarction （STEMI） patients with multivessel disease. However, the optimal timing of staged re- vascularization is still controversial. This study aimed to find the optimal timing of staged revascularization. Methods A total of 428 STEMI patients with multivessel disease who underwent primary PCI and staged PCI were included. According to the time interval between primary and staged PCI, patients were divided into three groups （〈 1 week, 1- weeks, and 2-12 weeks after primary PCI）. The primary endpoint was major adverse cardiovascular events （MACE）, a composite of all-cause death, non-fatal re-infarction, repeat revascularization, and stroke. Cox regression model was used to assess the association between staged PCI timing and risk of MACE. Results During the follow-up, 119 participants had MACEs. There was statistical difference in MACE incidence among the three groups （〈 1 week： 23.0%; 1-2 weeks： 33.0%; 2-12 weeks： 40.0%; P = 0.001）. In the multivariable adjustment model, the timing interval of staged PCI ≤ 1 week and l-2 weeks were both significantly associated with a lower risk of MACE [hazard ratio （HR）： 0.40, 95% confidence intervals （CI）： 0.24-4）.65; HR： 0.54, 95% CI： 0.3 lq3.93, respectively], mainly attributed to a lower risk of repeat revascularization （HR： 0.41, 95% CI： 0.24-0.70; HR： 0.36, 95% CI： 0.18-0.7）, compared with a strategy of 2-12 weeks later of primary PCI. Conclusions The optimal timing of staged PCI for non-culprit vessels should be within two weeks after primary PCI for STEMI patients.

Preliminary Studies on Predicting the Tropical Indian Ocean Sea Surface Temperature through Combined Statistical Methods and Dynamic ENSO Prediction

The sea surface temperature （SST） in the In- dian Ocean affects the regional climate over the Asian continent mostly through a modulation of the monsoon system. It is still difficult to provide an a priori indication of the seasonal variability over the Indian Ocean. It is widely recognized that the warm and cold events of SST over the tropical Indian Ocean are strongly linked to those of the equatorial eastern Pacific. In this study, a statistical prediction model has been developed to predict the monthly SST over the tropical Indian Ocean. This model is a linear regression model based on the lag relationship between the SST over the tropical Indian Ocean and the Nino3.4 （5°S-5°N, 170°W-120°W） SST Index. The pre- dictor （i.e., Nino3.4 SST Index） has been operationally predicted by a large size ensemble E1 Nifio and the Southern Oscillation （ENSO） forecast system with cou- pled data assimilation （Leefs_CDA）, which achieves a high predictive skill of up to a 24-month lead time for the equatorial eastern Pacific SST. As a result, the prediction skill of the present statistical model over the tropical In- dian Ocean is better than that of persistence prediction for January 1982 through December 2009.

An Artificial Neural Network-Based Snow Cover Predictive Modeling in the Higher Himalayas

With trends indicating increase in temperature and decrease in winter precipitation, a significant negative trend in snow-covered areas has been identified in the last decade in the Himalayas. This requires a quantitative analysis of the snow cover in the higher Himalayas. In this study, a nonlinear autoregressive exogenous model, an artificial neural network （ANN）, was deployed to predict the snow cover in the Kaligandaki river basin for the next 30 years. Observed climatic data, and snow covered area was used to train and test the model that captures the gross features of snow under the current climate scenario. The range of the likely effects of climate change on seasonal snow was assessed in the Himalayas using downscaled temperature and precipitation change projection from - HadCM3, a global circulation model to project future climate scenario, under the AIB emission scenario, which describes a future world of very rapid economic growth with balance use between fossil and non-fossil energy sources. The results show that there is a reduction of 9% to 46% of snow cover in different elevation zones during the considered time period, i.e., 2Oll to 2040. The 4700 m to 52oo m elevation zone is the most affected area and the area higher than 5200 m is the least affected. Overall, however, it is clear from the analysis that seasonal snow in the Kaligandaki basin is likely to be subject to substantialchanges due to the impact of climate change.

Characteristics of ventilation coefficient and its impact on urban air pollution

The temporal variation of ventilation coefficient was estimated and a simple model for the prediction of urban ventilation coefficient in Changsha was developed. Firstly, Pearson correlation analysis was used to investigate the relationship between meteorological parameters and mixing layer height during 2005-2009 in Changsha, China. Secondly, the multi-linear regression model between daytime and nighttime was adopted to predict the temporal ventilation coefficient. Thirdly, the validation of the model between the predicted and observed ventilation coefficient in 2010 was conducted. The results showed that ventilation coefficient significantly varied and remained high during daytime, while it stayed relatively constant and low during nighttime. In addition, the diurnal ventilation coefficient was distinctly negatively correlated with PM10 (particle with the diameter less than 10 μm) concentration in Changsha, China. The predicted ventilation coefficient agreed well with the observed values based on the multi-linear regression models during daytime and nighttime. The urban temporal ventilation coefficient could be accurately predicted by some simple meteorological parameters during daytime and nighttime. The ventilation coefficient played an important role in the PM10 concentration level.

Regression analysis of major parameters affecting the intensity of coal and gas outbursts in laboratory

Estimating the intensity of outbursts of coal and gas is important as the intensity and frequency of outbursts of coal and gas tend to increase in deep mining. Fully understanding the major factors contributing to coal and gas outbursts is significant in the evaluation of the intensity of the outburst. In this paper, we discuss the correlation between these major factors and the intensity of the outburst using Analysis of Variance(ANOVA) and Contingency Table Analysis(CTA). Regression analysis is used to evaluate the impact of these major factors on the intensity of outbursts based on physical experiments. Based on the evaluation, two simple models in terms of multiple linear and nonlinear regression were constructed for the prediction of the intensity of the outburst. The results show that the gas pressure and initial moisture in the coal mass could be the most significant factors compared to the weakest factor-porosity. The P values from Fisher's exact test in CTA are: moisture(0.019), geostress(0.290), porosity(0.650), and gas pressure(0.031). P values from ANOVA are moisture(0.094), geostress(0.077), porosity(0.420), and gas pressure(0.051). Furthermore, the multiple nonlinear regression model(RMSE: 3.870) is more accurate than the linear regression model(RMSE: 4.091).

Determination of Causal Effect in Observational Studies： Analysis of Correlated Data with Binary End-Points

Identifying the causal impact of＇ some intervention challenging when one is faced with correlated binary end-points in observational studies is a challenging task, and it is even more The statistical literature on analyzing such data is well documented. Dependence between observations from the same study subject in correlated data renders invalid the usual chi-square tests of independence and inflates the variance ofparameter estimates. Disaggregated approaches such as hierarchical linear models which are able to adjust for individual level covariate：s are favoured in the analysis of such data, thereby gaining power over aggregated and individual-level analyses. In this article the authors, therefore, address the issue of analyzing correlated data with dichotomous end-points by using hierarchical logistic regression, a generalization of the standard logistic regression model for independent outcomes.

Combined back-analysis method of ground stress based on refined geological modeling

A new back-analysis method of ground stress is proposed with comprehensive consideration of influence of topography, geology and nonlinear physical mechanical properties of rock on ground stress. This method based on non-uniform rational B-spline (NURBS) technology provides the means to build a refined three-dimensional finite element model with more accurate meshing under complex terrain and geological conditions. Meanwhile, this method is a back-analysis of ground stress with combination of multivariable linear regression model and neural network (ANN) model. Firstly, the regression model is used to fit approximately boundary loads. Regarding the regressed loads as mean value, some sets of boundary loads with the same interval are constructed according to the principle of orthogonal design, to calculate the corresponding ground stress at the observation positions using finite element method. The results (boundary loads and the corresponding ground stress) are added to the samples for ANN training. And on this basis, an ANN model is established to implement higher precise back-analysis of initial ground stress. A practical application case shows that the relative error between the inversed ground stress and observed value is mostly less than 10 %, which can meet the need of engineering design and construction requirements.

Validation of a method to predict hammer speed from cable force

Purpose： The purpose of this study was to develop and validate a method that would facilitate immediate feedback on linear hammer speed during training. Methods： Three-dimensional hammer head positional data were measured and used to calculate linear speed （calculated speed） and cable force. These data were used to develop two linear regression models （shifted and non-shifted） that would allow prediction of hammer speed from measured cable force data （predicted speed）. The accuracy of the two models was assessed by comparing the predicted and calculated speeds. Averages of the coefficient of multiple correlation （CMC） and the root mean square （RMS） of the difference between the predicted and calculated speeds for each throw of each participant were used to assess the level of accuracy of the predicted speeds. Results： Both regression models had high CMC values （0.96 and 0.97） and relatively low RMS values （1.27 m/s and 1.05 m/s） for the non-shifted and shifted models, respectively. In addition, the average percentage differences between the predicted and calculated speeds were 6.6% and 4.7% for the non-shifted and shifted models, respectively. The RMS differences between release speeds attained via the two regression models and those attained via three-dimensional positional data were also computed. The RMS differences between the predicted and calculated release speeds were 0.69 m/s and 0.46 m/s for the non-shifted and shifted models, respectively. Conclusion： This study successfully derived and validated a method that allows prediction of linear hammer speed from directly measured cable force data. Two linear regression models were developed and it was found that either model would be capable of predicting accurate speeds. However, data predicted using the shifted regression model were more accurate.

Variable Rate Technology and Cotton Yield Response in Texas

Variable Rate Technology （VRT） takes within-field variability into consideration and aims to match resource application to crop requirement. Even though Texas is the most important cotton producing state in the US, the rate of VRT adoption is very low here. Hence, analyzing the factors influencing the adoption and providing a regional estimate of the impact of VRT adoption on cotton yield is very important. This study used the 2009 Southern Cotton Precision Farming Survey to analyze the farm and farmer characteristics affecting the adoption of VRT among Texas cotton farmers and to empirically estimate the impact of adoption of VRT on cotton yield in Texas. A two-stage least square procedure with a logistic regression model in the first stage and a multiple linear regression model in the second stage was used to analyze the data. The study revealed that there are significant regional differences in adoption pattern within the state of Texas; and the farmers from the coastal region, where there is higher within-field variability, were more likely to adopt VRT compared to other regions. Younger farmers, farmers managing larger farms, and farmers who use computers for farming operations were more likely to adopt VRT. The results also showed that, on an average, the adoption of VRT does not lead to significant yield improvements for cotton in Texas. Since the impact of VRT adoption on yield is not significant, the source of economic advantage of VRT adoption in Texas may be the reduction of input cost.

Cardinal temperatures and required biological days from sowing to emergence of three millet species （common, foxtail, pearl millet）

The modeling of germination and seedling emergence is required for the construction of a simulation model of three species of millet （panicum miliaceum, pennisetum galucum and setaria italica）. This study provides the necessary temperature parameters to model these processes. For this purpose, different non-linear regression models including fiat, logistic, quadratic, sigmoidal, dent-like, segmented, beta and curvilinear were used. Root Mean Square of Errors, coefficient of determination and regression coefficients of predicted values versus observed were used to find the appropriate model. Investigating regression coefficients indicated that dent-like model has the least RMSE and a coefficient （RMSE=0.000009, a=0.0006） and the biggest R2 and b coefficient （R2=0.96, b=0.98） in common millet. These coefficients were （RMSE=0.01, a=0.005） and （R2=0.94, b=0.97）, and （RMSE=0.004, a=0.05） and （R2=0.99, b=0.99）, for beta in foxtail and pearl millet, respectively. According to these coefficients, dent-like, was chosen as the best model to describe the response of common millet germination to temperature （Tb=7~C and Tc=49.50℃）. Also beta, was chosen for foxtail millet （Tb=7℃, Tc=49.50℃）. Beta, was chosen as the best model for pearl millet （Tb=6.5 ℃ and To=4 ℃ ）. These parameters can be used in millet simulation models to predict sowing to emergence duration based on a thermal time concept. Also, required biological days from sowing to emergence using these models varied from 3.57, 4.29 and 5.54, for common millet, foxtail millet and pearl millet, respectively.

Trade Credit in the Crisis： Selling or Financing？

The work investigates the use of trade credit in Italy for reasons of a financial nature. The analysis considers Italian small and medium-sized enterprises （SMEs） and investigates, over the years of 2009-2011： the existence of functional relationships between the incidence of trade receivables and payables and corporate profitability; the existence of interdependencies between trade credit policy and trade debt policy; and the coexistence of interchangeable and complementary conditions between trade debts and bank loans and other sources of funding. To verify the research hypotheses, linear regression models on a yearly basis are used and these models are put under observation over the years of 2009-2011. We can conclude that there are interdependencies between trade credit policy and trade debt policy and that trade credit is a source of flexible way of financing, also available in periods of crisis, which has a positive effect on the profitability of SMEs and can be utilized as a complementary and substitute source of financing to bank loans.