回归模型中异性方差问题的克服

提出了回归分析中异性方差的检验和对估计结果带来的影响以及消除其异方差性的两种方法：对原模型进行变换和加权最小二乘法．

改进的各向异性标准化方差探测斜磁化磁异常源边界

针对存在强剩磁作用磁化方向不明的磁异常,本项研究探索直接处理斜磁化磁异常的识别,提出了基于磁力梯度张量模的各向异性边界探测方法.首先利用各向异性尺度改进了各向异性标准差的核函数,突出各向异性高斯函数的作用;结合磁力梯度张量模来消弱斜磁化的影响.数值实验模拟了一组复杂磁异常模型,在斜磁化条件下分析该研究方法的边界探测效果.实验表明:改进方法,即磁力梯度张量模的各向异性标准化方差,它可以探测非垂直磁化磁异常的磁源边界;同时指出,改进方法比基于三维解析信号振幅的各向异性标准化方差对磁化方向的依赖性更小.将该方法应用于中国西部某磁铁矿集区的精细探测,在非垂直磁化条件下对实测磁异常直接进行边界探测,获得了较为理想的处理结果.

各向异性标准化方差计算重磁源边界

在重磁源边界定位方法中,传统的梯度方法易受干扰的影响使计算的边界混乱,而且在弱异常处由于叠加异常的影响很难识别场源边界.本文首先利用坐标旋转构造了各向异性高斯函数,提出了各向异性标准化方差计算重磁源边界的方法.理论分析与模型实验详细阐明了该方法的数学含义,并通过干扰分析验证了方法的稳定性与有效性,结合中扬子地区航磁异常处理实例,表明通过计算各向异性标准化方差,可以有效地确定重磁源边界,尤其对微弱异常能够实现较好的边界定位,计算的边界分辨率高且信息丰富,有利于资料的综合解释.

基于散度J_C或J_B准则的母体方差差异性的模式识别

本文利用模式识别中的准则函数JC或JB作基准，详细阐述了处理母体方差差异性问题的方法，并与统计检验法作了比较，且以实例验证了方法的效果。

生物利用度试验中有关统计分析的几个问题

生物利用度试验是药物制剂生物等效性(Bioequivalence)评价的方法之一,广泛用于评价药物效应与血药浓度相关的药物两种或两种以上制剂间是否生物等效,包括同一药物的不同处方或工艺间、不同制造商的同一规格产品间、仿制药与专利药间是否生物等效,也适用于评价具有同一活性物质不同的血管外给药制剂间(例如片剂和胶囊剂)是否生物等效.

Effect of aggregation interval on vehicular traffic flow heteroscedasticity

The effect of the aggregation interval on vehicular traffic flow heteroscedasticity is investigated using real-world traffic flow data collected from the motorway system in the United Kingdom. 30 traffic flow series are generated using 30 aggregation intervals ranging from 1 to 30 min at 1 min increment, and autoregressive integrated moving average （AR/MA） models are constructed and applied in these series, generating 30 residual series. Through applying the portmanteau Q-test and the Lagrange multiplier （LM） test in the residual series from the ARIMA models, the heteroscedasticity in traffic flow series is investigated. Empirical results show that traffic flow is heteroscedastJc across these selected aggregation intervals, and longer aggregation intervals tend to cancel out the noise in the traffic flow data and hence reduce the heteroscedasticity in traffic flow series. The above findings can be utilized in the development of reliable and robust traffic management and control systems.

The analysis and application of simplified two-parameter moveout equation for C-waves in VTI anisotropy media

Several parameters are needed to describe the converted-wave （C-wave） moveout in processing multi-component seismic data, because of asymmetric raypaths and anisotropy. As the number of parameters increases, the converted wave data processing and analysis becomes more complex. This paper develops a new moveout equation with two parameters for C-waves in vertical transverse isotropy （VTI） media. The two parameters are the C-wave stacking velocity （Vc2） and the squared velocity ratio （7v,i） between the horizontal P-wave velocity and C-wave stacking velocity. The new equation has fewer parameters, but retains the same applicability as previous ones. The applicability of the new equation and the accuracy of the parameter estimation are checked using model and real data. The form of the new equation is the same as that for layered isotropic media. The new equation can simplify the procedure for C-wave processing and parameter estimation in VTI media, and can be applied to real C-wave processing and interpretation. Accurate Vc2 and Yvti can be deduced from C-wave data alone using the double-scanning method, and the velocity ratio model is suitable for event matching between P- and C-wave data.

On gender differences in language acquisition

English learning is influenced by many factors which affect directly or indirectly the students＇ English acquirement. Among these, the learner himself or herself is the most direct and important. This passage emphasizes the point of English educational psychology and from it we can see that the motivation factor, ability factor and intellect factor affect the students＇ English learning most. Girls＇ internal motivation is stronger than boys＇ in the foreign language studying and most of the girls aim at gaining English knowledge. The process of English learning itself can make them contented and basically they will not be interrupted by the external factors.

Similarities and Differences Between Freundlich Kinetic Equation and Two-Constant Equation

A mathematical expression of Freundlich kinetic equation, 1nS=A'+B'1nt, is presented, and the physical meanings of its parameters are indicated. Although the Freundlich kinetic equation and the two-constant equation are the same in the form, the derivation of the Freundlich kinetic equation is precise, while the deriVation of the two-constant equation has some contradictions and is unreasonable. And it is suggested that the Freundlich kinetic equation should have priority over the two-constant equation to be used.

The Particularity of Identity in Amin Maalouf＇ s Ports of Call

This study explores the intricate situation of the coexistence of different identities in Amin Maalouf＇ s Ports of Call （1996）. It contends that identity is complex, flux, and not limited to what is inherited; it is rather a psychological, political, and social amalgamation. Thus, each individual has a unique and particular identity, which is completely different from the others＇. This study is a theoretical and analytical survey of Maalouf＇s Ports of Call. It aims at proving that this novel is an example that Maalouf provides to show the challenges that characters of different identities face, and the obstacles that hinder them from assimilation. The argument is mainly based on Edward Said＇s theories that have opened up discussions about Otherness and multiculturalism, alongside with other postcolonial critics, such as Homi Bhabha. Maalouf＇s book In the Name of Identity： Violence and the Need to Belong （1996） is also integral to this study. The study concludes that it might be possible for people, in parallel with the characters of the novel, to challenge the identity predicament that the world is witnessing nowadays, and accept diversities as a way of life, rather than a reason for waging wars.

Analysis of gender＇s role on voluntary tendency of potential/active volunteers via logistic regression modeling： The case of Canakkale Onsekiz Mart University

From economy to political administrations, education to health, environment to human rights, many problems we met have gained a global importance in recent days. Existing state systems, political parties and nation states are not adequate for solving these problems in question effectively on their own. Not only governments and local authorities but also voluntary organizations based on completely voluntary activities have significant roles in solving these problems. Effective performance of voluntary organizations depends on increasing volunteer population. Individuals＇ attitudes or their perception of understanding volunteerism play an important role in their contributions to voluntary organizations. The aim of this study is to determine individuals＇ ways of perceiving volunteerism concept and their tendency towards it. Furthermore, differences between men and women＇s perception and attitudes towards volunteerism concept have been examined. For this purpose, a survey has been conducted over university students of bachelor＇s degree. Tendencies and attitudes towards volunteerism compared to gender differences have been tested via logistic regression method. Research results reveal that women take part in voluntary activities more than men and women perceive volunteerism as ＂a political position＂ while men perceive volunteerism as ＂a learning atmosphere and learning process＂.

Gender Differences in Auditory Perception and Computational Divided Attention Tasks

Women have been stereotyped as better multitaskers when compared to their male counterparts. The purpose of this study is to investigate whether there are differences in gender performance when performing cognitive combined tasks. Twenty-four graduate students （twelve females and twelve males） volunteered to participate in the study. The task requires participants to indicate when they perceive a change in the intensity of an auditory signal while simultaneously solving algebraic problems. Multivariate Analysis of Variance （MANOVA） results reveal no significant differences between genders when performing the combined tasks （p = 0.1831 and 2 = 0.7891） although the average number of false alarms made during the combined tasks by males is nearly 11% higher than the average number of false alarms made by females. However, （Multivariate Analysis of Variance） ANOVA results for the combined tasks show that males outperform females on the computational task while listening for changes in the auditory signal F（1, 22） - 5.09, p 〈 0.03, but there are no significant differences in their ability to detect noise intensity variation or in the number of false alarms made while multitasking. For the single task analysis the ANOVAs indicate no significant differences in signal detection task performance, computational task performance, or the number of false alarms made by males and females.

Effect of Heteroscedastic Variance Covariance Matrices on Two Groups Linear Classification Techniques

The authors investigate the comparative classification performance of the two groups linear classification techniques. They compared the Fisher linear classification analysis, its robust version based on the minimum covariance determinant with the Filter linear classification rule and the linear combination linear classification technique. These procedures are investigated using laboratory reared aedes albopictus mosquito data set and simulated data set generated based on heteroscedastic covariance matrices with various proportion of contamination. The evaluation procedure is based on the effect of contamination on the mean probabilities of correct classification obtain for each technique. The comparative analysis revealed that the robust Fisher linear classification rule and the linear combination linear classification rule are robust and comparable than the other procedures.

GENERALIZED CONFIDENCE REGIONS OF FIXED EFFECTS IN THE TWO-WAY ANOVA

The authors discuss the unbalanced two-way ANOVA model under heteroscedasticity. By taking the generalized approach, the authors derive the generalized p-values for testing the equality of fixed effects and the generalized confidence regions for these effects. The authors also provide their frequentist properties in large-sample cases. Simulation studies show that the generalized confidence regions have good coverage probabilities.

Uniformity and Regional Variation: The Xiangli System in the Sui Dynasty

As defined in a decree issued in the spring of 583,the three heads or sanzhang system,designed to be implemented chiefly in the old Northern Qi area in Shandong,basically followed the Northern Qi version of 564,with slight modifications.With the setting up of a system of xiang heads(xiangzheng乡正)who would hear disputes among the common people,as recommended in Su Wei’s memorial of the same year,the judicial position of xiangzheng coexisted with the administrative positions of the three-heads(or two-heads)system.The xiangli(乡里)system announced in the edict of 589 targeted the territory previously under the Chen dynasty;it was basically a continuation of the xiangli system of rural control originally based on a Han dynasty model and followed since then in the south under the Eastern Jin and the Southern dynasties.With the reform of the bureaucratic system in 607,the xiangli system centered on xiangzheng and lizhang became the basic system of rural administration under the Sui dynasty.In the course of its design and creation,the system had to take into account the institutions already existing in the target area and the question of feasibility.Thus“inconsistency”or“regional variation”was built into the system.However,in actual practice there was a tendency toward convergence that led to uniformity of implementation.In Chinese history,the coexistence of regional variation and uniformity was a marked feature of the formation and implementation of different systems.

ASYMPTOTIC NORMALITY OF WAVELET ESTIMATOR IN HETEROSCEDASTIC MODEL WITH α-MIXING ERRORS

Consider heteroscedastic regression model Yni= g（xni） ＋ σniεni （1 〈 i 〈 n）, where σ2ni= f（uni）, the design points （xni, uni） are known and nonrandom, g（.） and f（.） are unknown functions defined on closed interval [0, 1], and the random errors （εni, 1 ≤i≤ n） axe assumed to have the same distribution as （ξi, 1 ≤ i ≤ n）, which is a stationary and a-mixing time series with Eξi =0. Under appropriate conditions, we study asymptotic normality of wavelet estimators of g（.） and f（.）. Finite sample behavior of the estimators is investigated via simulations, too.