COX MULTIVARIATE REGRESSION ANALYSIS OF RECURRENCE FACTORS FOR COLONIC CARCINOMA

Objective: To determine the independent prognostic factors in the recurrence of colonic carcinoma after curative resection. Methods: Two hundred and one patients undergoing curative resections for colonic carcinoma were investigated by univariate and Cox multivariate regression analyses. Ten factors contributed to the rate were analyzed. Results: Dukes stages, obstruction, postoperative chemotherapy as well as the growth manner of the tumor were significantly associated with the recurrence rate of colonic carcinoma (P<0.05) by univariate analysis, while Dukes stages, obstruction, and postoperative chemotherapy were significant factors by the multivariate analysis. Conclusion: Dukes stages, obstruction, and postoperative chemotherapy are independent prognostic factors in the recurrence of colonic carcinoma.

Construction of Inorganic Elemental Fingerprint and Multivariate Statistical Analysis of Marine Traditional Chinese Medicine Meretricis concha from Rushan Bay

Meretricis concha is a kind of marine traditional Chinese medicine(TCM), and has been commonly used for the treatment of asthma and scald burns. In order to investigate the relationship between the inorganic elemental fingerprint and the geographical origin identification of Meretricis concha, the elemental contents of M. concha from five sampling points in Rushan Bay have been determined by means of inductively coupled plasma optical emission spectrometry(ICP-OES). Based on the contents of 14 inorganic elements(Al, As, Cd, Co, Cr, Cu, Fe, Hg, Mn, Mo, Ni, Pb, Se, and Zn), the inorganic elemental fingerprint which well reflects the elemental characteristics was constructed. All the data from the five sampling points were discriminated with accuracy through hierarchical cluster analysis(HCA) and principle component analysis(PCA), indicating that a four-factor model which could explain approximately 80% of the detection data was established, and the elements Al, As, Cd, Cu, Ni and Pb could be viewed as the characteristic elements. This investigation suggests that the inorganic elemental fingerprint combined with multivariate statistical analysis is a promising method for verifying the geographical origin of M. concha, and this strategy should be valuable for the authenticity discrimination of some marine TCM.

Structure Sorting of Multiple Macromolecular States in Heterogeneous Cryo-EM Samples by 3D Multivariate Statistical Analysis

Heterogeneity of biological samples is usually considered a major obstacle for three-dimensional (3D) structure determination of macromolecular complexes. Heterogeneity may occur at the level of composition or conformational variability of complexes and affects most 3D structure determination methods that rely on signal averaging. Here, an approach is described that allows sorting structural states based on a 3D statistical approach, the 3D sampling and classification (3D-SC) of 3D structures derived from single particles imaged by cryo electron microscopy (cryo-EM). The method is based on jackknifing & bootstrapping of 3D sub-ensembles and 3D multivariate statistical analysis followed by 3D classification. The robustness of the statistical sorting procedure is corroborated using model data from an RNA polymerase structure and experimental data from a ribosome complex. It allows resolving multiple states within heterogeneous complexes that thus become amendable for a structural analysis despite of their highly flexible nature. The method has important implications for high-resolution structural studies and allows describing structure ensembles to provide insights into the dynamics of multi-component macromolecular assemblies.

Quality assessment of Jinhongtang Granule using UFLC-MS/MS and multivariate statistical analysis

Jinhongtang is a traditional Chinese medicine formula composed of Rheum palmatum L.stem,Sargentodoxa cuneata stem,and Taraxacum mongolicum and is used for the treatment of sepsis.However,quality assessment method for Jinhongtang is not available.In present study,we developed a UFLC-MS/MS method to determine 16 analytes in 20 batches of home-made and commercial Jinhongtang.Multivariate statistical analysis revealed the significant differences in the quality of home-made and commercial Jinhongtang and the difference in the quality of home-made samples was more significant.The integrated strategy based on UFLC-MS/MS and multivariate statistical analysis provided a new basis for the overall quality assessment of Jinhongtang.

Study on the Relationship between Soil and Environment Based on Multivariate Statistical Analysis

[Objective] The study aimed to study the relationship between soil and environment on the basis of multivariate statistical analysis. [ Method] Through field investigation, sampling and laboratory analysis, we discussed the relationship between soil properties and environmental factors in Mizhi County, North Shaanxi by using Canoco multivariate statistical analysis. [ Result]According to the effects of various environmental factors on soil properties, the influencing order of environmental factors was land use way 〉 vegetation type 〉 vegetation restoration years 〉 vegeta- tion coverage 〉 slope aspect 〉 gradient 〉 elevation. In a word, soil properties were significantly affected by land use way and vegetation type which were the most important environmental factors of soil properties in spatial variation, while vegetation restoration years were closely related to the ac- cumulation of soil nutrients. [ Condusion]The research could provide theoretical references for the construction of ecological environment in Loess Plateau of China.

Profiling the Change of Key Chemical Ingredients in Combination of Aconitum carmichaeli Debx. and Bletilla striata (Thunb.) Reichb.f. by UPLC-QTOF/MS with Multivariate Statistical Analysis

In the present study, an ultra performance liquid chromatography coupled with quadrupole time-of-flight mass spectrometry(UPLC-QTOF/MS) based chemical profiling approach to rapidly evaluate chemical diversity after codecocting of the combination of Aconitum carmichaeli Debx.(wu-tou in Chinese, WT) and Bletilla striata(Thunb.) Reichb.f.(bai-ji in Chinese, BJ) incompatible pair. Two different kinds of decoctions, namely WT-BJ mixed decoction: mixed water extract of each individual herbs, and WT-BJ co-decoction: water extract of mixed two constituent herbs, were prepared. Batches of these two kinds of decoction samples were subjected to UPLC-QTOF/MS analysis, the datasets of tR-m/z pairs, ion intensities and sample codes were processed with supervised orthogonal partial least squared discriminant analysis(OPLS-DA) to holistically compare the difference between these two kinds of decoction samples. Once a clear classification trend was found in score plot, extended statistical analysis was performed to generate S-plot, in which the variables(tR-m/z pair) contributing most to the difference were clearly depicted as points at the two ends of "S", and the components that correlate to these ions were regarded as the most changed components during co-decocting of the incompatible pair. The identities of the changed components can be identified by comparing the retention times and mass spectra with those of reference compounds and/or tentatively assigned by matching empirical molecular formulae with those of the known compounds published in the literatures. Using the proposed approach, global chemical difference was found between mixed decoction and co-decoction, and hypaconitine, mesaconitine, deoxyaconitine, aconitine, 10-OH-mesaconitine, 10-OH-aconitine and deoxyhypaconitine were identified as the most changed toxic components of the combination of WT-BJ incompatible pair during co-decocting. It is suggested that this newly established approach could be used to practically reveal the possible toxic components changed/increased of the herbal combination taboos, e.g. the Eighteen Incompatible Medications(Shi Ba Fan), in traditional Chinese medicines.

Modeling the Drilling Process of Aluminum Composites Using Multiple Regression Analysis and Artificial Neural Networks

In recent years, aluminum-matrix composites (AMCs) have been widely used to replace cast iron in aerospace and automotive industries. Machining of these composite materials requires better understanding of cutting processes re- garding accuracy and efficiency. This study addresses the modeling of the machinability of self-lubricated aluminum /alumina/graphite hybrid composites synthesized by the powder metallurgy method. In this study, multiple regression analysis (MRA) and artificial neural networks (ANN) were used to investigate the influence of some parameters on the thrust force and torque in the drilling processes of self-lubricated hybrid composite materials. The models were identi- fied by using cutting speed, feed, and volume fraction of the reinforcement particles as input data and the thrust force and torque as the output data. A comparison between two prediction methods was developed to compare the prediction accuracy. ANNs showed better predictability results compared to MRA due to the nonlinearity nature of ANNs. The statistical analysis accompanied with artificial neural network results showed that Al2O3, Gr and cutting feed (f) were the most significant parameters on the drilling process, while spindle speed seemed insignificant. Since the spindle speed was insignificant, it directed us to set it either at the highest spindle speed to obtain high material removal rate or at the lowest spindle speed to prolong the tool life depending on the need for the application.

Joint multivariate statistical model and its applications to synthetic earthquake predic-tion

针对目前地震综合预报中的一些问题，利用近30年来迅速发展的多元统计分析中主成分分析、判别分析组成多元统计组合模型，在众多的地震预报指标(预报因子)中采用信息最大化方法，选择对中期预测信息累积贡献率大于90％地震预报指标，分别进行相关分析、预测、检验，最终应用马氏距离判别作外推综合预报；并以华北地区(30°～42°N，108°125°E)为例进行模型的应用检验，初步研究已取得了较好的效果．

Joint multivariate statistical model and its applications to the synthetic earthquake prediction

Considering the problems that should be solved in the synthetic earthquake prediction at present, a new model is proposed in the paper. It is called joint multivariate statistical model combined by principal component analysis with discriminatory analysis. Principal component analysis and discriminatory analysis are very important theories in multivariate statistical analysis that has developed quickly in the late thirty years. By means of maximization information method, we choose several earthquake prediction factors whose cumulative proportions of total sam-ple variances are beyond 90% from numerous earthquake prediction factors. The paper applies regression analysis and Mahalanobis discrimination to extrapolating synthetic prediction. Furthermore, we use this model to charac-terize and predict earthquakes in North China (30~42N, 108~125E) and better prediction results are obtained.

Application of multivariate statistical techniques in assessment of surface water quality in Second Songhua River basin,China

Multivariate statistical techniques,such as cluster analysis(CA),discriminant analysis(DA),principal component analysis(PCA) and factor analysis(FA),were applied to evaluate and interpret the surface water quality data sets of the Second Songhua River(SSHR) basin in China,obtained during two years(2012-2013) of monitoring of 10 physicochemical parameters at 15 different sites.The results showed that most of physicochemical parameters varied significantly among the sampling sites.Three significant groups,highly polluted(HP),moderately polluted(MP) and less polluted(LP),of sampling sites were obtained through Hierarchical agglomerative CA on the basis of similarity of water quality characteristics.DA identified p H,F,DO,NH3-N,COD and VPhs were the most important parameters contributing to spatial variations of surface water quality.However,DA did not give a considerable data reduction(40% reduction).PCA/FA resulted in three,three and four latent factors explaining 70%,62% and 71% of the total variance in water quality data sets of HP,MP and LP regions,respectively.FA revealed that the SSHR water chemistry was strongly affected by anthropogenic activities(point sources:industrial effluents and wastewater treatment plants;non-point sources:domestic sewage,livestock operations and agricultural activities) and natural processes(seasonal effect,and natural inputs).PCA/FA in the whole basin showed the best results for data reduction because it used only two parameters(about 80% reduction) as the most important parameters to explain 72% of the data variation.Thus,this work illustrated the utility of multivariate statistical techniques for analysis and interpretation of datasets and,in water quality assessment,identification of pollution sources/factors and understanding spatial variations in water quality for effective stream water quality management.

New Method for Multivariate Statistical Process Monitoring

A new method using discriminant analysis and control charts is proposed for monitoring multivariate process operations more reliably.Fisher discriminant analysis （FDA） is used to derive a feature discriminant direction （FDD） between each normal and fault operations,and each FDD thus decided constructs the feature space of each fault operation.Individuals control charts （XmR charts） are used to monitor multivariate processes using the process data projected onto feature spaces.Upper control limit （UCL） and lower control limit （LCL） on each feature space from normal process operation are calculated for XmR charts,and are used to distinguish fault from normal.A variation trend on an XmR chart reveals the type of relevant fault operation.Applications to Tennessee Eastman simulation processes show that this proposed method can result in better monitoring performance than principal component analysis （PCA）-based methods and can better identify step type faults on XmR charts.

The use of hydrogeochemical analyses and multivariate statistics for the characterization of thermal springs in the Constantine area, Northeastern Algeria

This paper deals with the results of a hydrogeochemistry study on the thermal waters of the Constantine area, Northeastern Algeria, using geochemical and statistical tools. The samples were collected in December2016 from twelve hot springs and were analyzed for physicochemical parameters(electric conductivity, p H,total dissolved solids, temperature, Ca, Mg, Na, K, HCO_3,Cl, SO_4, and SiO_2). The waters of the thermal springs have temperatures varying from 28 to 51 °C and electric conductivity values ranging from 853 to 5630 l S/cm. Q-mode Cluster analysis resulted in the determination of two major water types: a Ca–HCO_3–SO_4 type with a moderate salinity and a Na–K–Cl type with high salinity. The plot of the major ions versus the saturation indices suggested that the hydrogeochemistry of thermal groundwater is mainly controlled by dissolution/precipitation of carbonate minerals, dissolution of evaporite minerals(halite and gypsum), and ion exchange of Ca(and/or Mg) by Na. The Gibbs diagram shows that evaporation is another factor playing a minor role. Principal Component Analysis produced three significant factors which have 88.2% of totalvariance that illustrate the main processes controlling the chemistry of groundwaters, which are respectively: the dissolution of evaporite minerals(halite and gypsum), ion exchange, and dissolution/precipitation of carbonate minerals. The subsurface reservoir temperatures were calculated using different cation and silica geothermometers and gave temperatures ranging between 17 and 279 °C. The Na–K and Na–K-Ca geothermometers provided high temperatures(up to 279 °C), whereas, estimated geotemperatures from K/Mg geothermometers were the lowest(17–53 °C). Silica geothermometers gave the most reasonable temperature estimate of the subsurface waters overlap between 20 and 58 °C, which indicate possible mixing with cooler Mg groundwaters indicated by the Na–K–Mg plot in the immature water field and in silica and chloride mixing models. The results of stable isotope analyses(δ^(18) O and δ~2 H) suggest that the origin of thermal water recharge is precipitation, which recharged from a higher altitude(600–1200 m) and infiltrated through deep faults and fractures in carbonate formations. They circulate at an estimated depth that does not exceed 2 km and are heated by a high conductive heat flow before rising to the surface through faults that acted as hydrothermal conduits.During their ascent to the surface, they are subjected to various physical and chemical changes such as cooling by conduction and change in their chemical constituents due to the mixing with cold groundwaters.

Assessment of Spatio-Temporal Variations in Water Quality of Shailmari River, Khulna (Bangladesh) Using Multivariate Statistical Techniques

Surface water has become one of the most vulnerable resources on the earth due to deterioration of its quality from diverse sources of pollution. Understanding of the spatiotemporal distribution of pollutants and identification of the sources in the river systems is a prerequisite for the protection and sustainable utilization of the water resources. Multivariate statistical techniques such as Principal Component Analysis (PCA) and Factor Analysis (FA) were applied in this study to investigate the temporal and spatial variations of water quality and appoint the major factors of pollution in the Shailmari River system. Water quality data for 14 physicochemical parameters from 11 monitoring sites over the year of 2014 in three sampling seasons were collected and analyzed for this study. Kruskal-Wallis test showed significant (p < 0.01) temporal and spatial variations in all of the water quality parameters of the river water. Principal component analysis (PCA) allowed extracting the contributing parameters affecting the seasonal water quality in the river system. Scatter plots of the PCs showed the tidal and spatial variation within river system and identified parameters controlling the behavior in each case. Factor analysis (FA) further reduced the data and extracted factors which are significantly responsible for water quality variation in the river. The results indicate that the parameters controlling the water quality in different seasons are related with salinity, anthropogenic pollution (sewage disposal, effluents) and agricultural runoff in pre-monsoon;precipitation induced surface runoff in monsoon;and erosion, oxidation or organic pollution (point and non-point sources) in post-monsoon. Therefore, the study reveals the applicability and usefulness of the multivariate statistical methods in assessing water quality of river by identifying the potential environmental factors controlling the water quality in different seasons which might help to better understand, monitor and manage the quality of the water resources.

Water Quality Assessment of a Tropical Mexican Lake Using Multivariate Statistical Techniques

Water quality of Mexican tropical lake Chapala was assessed through multivariate statistical techniques, cluster analysis (CA) and principal component analysis (PCA) at ten different monitoring sites for ten physicochemical variables and six metals. This study evaluated and interpreted complex water quality data sets and apportioned of pollution sources to get better information about water quality. From descriptive statistics results, the highest concentrations of metals occurred during the dry season, and this trend was explained by the fact that an unusual rainy event occurred during the month of February 2009 and brought metals into the lake by runoffs from nearby mountains. According to international criteria for water consumption by aquatic organisms [USEPA], only Zn concentration values were below these criteria whereas the values of Ni, Pb, Cd and Fe were above the corresponding values set in these criteria (Ni: 52 μg&middot;L-1, Pb: 2.5 μg&middot;L-1, Cd: 0.25 μg&middot;L-1, and Fe: 1000 μg&middot;L-1). The correlations were observed by PCA, which were used to classify the samples by CA, based on the PCA scores. Seven significant cluster groups of sampling locations—(sites 4 and 5), (sites 3 and 9), (site 7), (site 10), (sites 2 and 6), (site 8) and (site 1)— were detected on the basis of similarity of their water quality. The results revealed that the stress exerted on the lake caused by waste sources follows the order: domestic > agricultural > industrial.

Rapid Analysis and Identification of Absorbed Components and Their Metabolites of Yuanhu Zhitong Dropping Pill in Rat Plasma and Brain Tissue Using UPLC-Q-TOF/MS with Multivariate Statistical Analysis

Objective To establish an effective approach for rapid and comprehensive analysis on the absorbed and metabolic components in rats after ig administration of Yuanhu Zhitong Dropping Pill（YHZT）. Methods Based on the combination of UPLC-Q-TOF/MS and multivariate statistical analysis, the absorbed prototype constituents and their metabolites in rat plasma were rapidly analyzed and identified, and the components absorbed into brain were further identified by comparing the extracted ion chromatograms（EICs） of control and brain tissue samples of dosed rats. Results A total of 38 YHZT-related xenobiotic compounds were detected and identified as the potential bioactive constituents in rat plasma, including 24 absorbed prototype constituents and 14 metabolites. In particular, of all prototype constituents, 14 were also detected in rat brain tissue, indicating that they could penetrate the blood-brain barrier and enter into brain. Conclusion An effective method is established and applied to analyze the potential bioactive constituents in YHZT, which provides a pathway to further investigate the pharmacological pattern and mechanism of YHZT.

Combined Use of Multivariate Statistical Analysis and Hydrochemical Analysis for Groundwater Quality Evolution: A Case Study in North Chain Plain

Understanding the controlling factor of groundwater quality can enhance promoting sustainable development of groundwater resources. To this end, multivariate statistical analysis（MA） and hydrochemical analysis were introduced in this work. The results indicate that the canonical discriminant function with 7 parameters was established using the discriminant analysis（DA） method, which can afford 100% correct assignation according to the 3 different clusters（good water（GW）, poor water（PW）, and very poor water（VPW）） obtained from cluster analysis（CA）. According to factor analysis（FA）, 8 factors were extracted from 25 hydrochemical elements and account for 80.897% of the total data variance, suggesting that groundwater with higher concentrations of sodium, calcium, magnesium, chloride, and sulfate in southeastern study area are mainly affected by the natural process; the higher level of arsenic and chromium in groundwater extracted from northwestern part of study area are derived by industrial activities; domestic and agriculture sewage have important contribution to copper, iron, iodine, and phosphate in the northern study area. Therefore, this work can help identify the main controlling factor of groundwater quality in North China plain so as to make better and more informed decisions about how to achieve groundwater resources sustainable development.

Multivariate Statistical Process Monitoring of an Industrial Polypropylene Catalyzer Reactor with Component Analysis and Kernel Density Estimation

Abstract Data-driven tools, such as principal component analysis （PCA） and independent component analysis （ICA） have been applied to different benchmarks as process monitoring methods. The difference between the two methods is that the components of PCA are still dependent while ICA has no orthogonality constraint and its latentvariables are independent. Process monitoring with PCA often supposes that process data or principal components is Gaussian distribution. However, this kind of constraint cannot be satisfied by several practical processes. To ex-tend the use of PCA, a nonparametric method is added to PCA to overcome the difficulty, and kernel density estimation （KDE） is rather a good choice. Though ICA is based on non-Gaussian distribution intormation, .KDE can help in the close monitoring of the data. Methods, such as PCA, ICA, PCA.with .KDE（KPCA）, and ICA with KDE,（KICA）, are demonstrated and. compared by applying them to a practical industnal Spheripol craft polypropylene catalyzer reactor instead of a laboratory emulator.

Advanced reliability analysis of slopes in spatially variable soils using multivariate adaptive regression splines

This study aims to extend the multivariate adaptive regression splines(MARS)-Monte Carlo simulation(MCS) method for reliability analysis of slopes in spatially variable soils. This approach is used to explore the influences of the multiscale spatial variability of soil properties on the probability of failure(P_f) of the slopes. In the proposed approach, the relationship between the factor of safety and the soil strength parameters characterized with spatial variability is approximated by the MARS, with the aid of Karhunen-Loeve expansion. MCS is subsequently performed on the established MARS model to evaluate Pf.Finally, a nominally homogeneous cohesive-frictional slope and a heterogeneous cohesive slope, which are both characterized with different spatial variabilities, are utilized to illustrate the proposed approach.Results showed that the proposed approach can estimate the P_f of the slopes efficiently in spatially variable soils with sufficient accuracy. Moreover, the approach is relatively robust to the influence of different statistics of soil properties, thereby making it an effective and practical tool for addressing slope reliability problems concerning time-consuming deterministic stability models with low levels of P_f.Furthermore, disregarding the multiscale spatial variability of soil properties can overestimate or underestimate the P_f. Although the difference is small in general, the multiscale spatial variability of the soil properties must still be considered in the reliability analysis of heterogeneous slopes, especially for those highly related to cost effective and accurate designs.

Chemical comparison of dried rehmannia root and prepared rehmannia root by UPLC-TOF MS and HPLC-ELSD with multivariate statistical analysis

To identify the chemical differences which lead to the different therapeutic effects of dried rehmannia root(DRR)and prepared rehmannia root(PRR),we compared the chemical composition of decoctions of randomly purchased DRR and PRR using ultra performance liquid chromatography(UPLC)coupled with time-of-fight mass spectrometry and high performance liquid chromatography(HPLC)coupled with evaporative light scattering detection(ELSD)with the aid of multivariate statistical analysis.Both approaches clearly revealed compositional and quantitative differences between DRR and PRR.UPLC-MS data indicated stachyose,rehmaiono-side A(or rehmaionoside B),acteoside(or forsythiaside,or isoacteoside),6-O-coumaroylajugol(or 6-O-E-feruloylajugol,or 6-O-Z-feruloylajugol)as important discriminators between DRR and PRR decoctions.HPLC-ELSD analysis showed that the content of fructose in the decoctions of PRR was about four times greater than that of DRR(P<10^(-5)),while sucrose content in the decoctions of PRR was only about one seventh of that in DRR(P<0.01).Our results suggest that some compounds,such as fructose,stachyose and rehmaionoside,may be responsible for the differing therapeutic effects of DRR and PRR.Furthermore,improvements in quality control for PRR,which is currently lacking in the Chinese Pharmacopoeia,are recommended.

Operational method for determining bottom hole pressure in mechanized oil producing wells,based on the application of multivariate regression analysis

One of the major tasks of monitoring production well operations is to determine bottom-hole flowing pressure.The overwhelming majority of wells in the Perm Krai are serviced using borehole pumps,which makes it difficult to take direct bottom-hole flowing pressure measurements.The bottomhole filtration pressure(BHFP)in these wells is very often determined by recalculating the parameters measured at the well mouth(annulus pressure,dynamic fluid level depth).The recalculation is done by procedures based on analytically determining the characteristics of the gas-liquid mixture in the wellbore,which is very inconsistent to perform due to the mixture's complex behavior.This article proposes an essentially different approach to BHFP measurements that relies on the mathematical processing of the findings of more than 4000 parallel mouth and deep investigations of the oil production wells of a large oil-production region.As a result,multivariate mathematical models are elaborated that allow reliably determining the BHFP of oil-production wells in operation.