On the Performance of Some Classification Rules for Qualitative Data for Simulated Underlying Distributions

Two linear functions for discriminating with qualitative variables (Fisher's linear discriminant function and the independence rule) are compared with the general multinomial procedure, a rule based on Lancaster's definition of higher order interactions and the quadratic discriminant function. The evaluation of these functions is carried out within Monte Carlo experiments. Various types of underlying distributions generated by a special algorithm are used.     

Two-Group Classification when Both Groups are Mixtures of Normals

In this paper we consider a two-group discriminant analysis problem where each group is a mixture of two subgroups. Based upon data from a clinical study of alcohol involvement and diseases, simulation experiments were performed for three different configurations of means and covariance matrices. Expected actual non-error rates are estimated for the linear, quadratic, and kernel discriminant functions for sample sizes 30, 50, 75, 100, 150 and 200. A conclusion of the article is that the kernel discriminant function performs as well as or better than quadratic discriminant function. However, the linear discriminant function was clearly inferior to either the quadratic or kernel discriminant functions.     

Revisiting historical Khoe-San skeletal remains in European collections: A search for identity through craniometric analysis

As the identity of a large number of Khoe-San skeletal material in European collections recently came into question during its documentation, a re-evaluation of the remains by employing a non-invasive method such as craniometrics was done to investigate the biological affinity. For this purpose, gene flow and population diversity present within the group, as well as between the study sample (N = 63) and other modern and historic population groups from southern, central and east Africa were explored. Available comparative groups included the historic Khoe-San from Riet River (N = 31), the Sotho-Tswana from southern Africa (N = 61), the Basuku from central Africa (N = 66) and the Bahutu (N = 53) and Teita (N = 24) from east Africa. Ten craniometric variables were selected and used to perform population structure analysis based on model bound quantitative genetics and multiple discriminant function analysis (MDA). Quantitative genetic distances revealed that the Khoe-San sample was closest to the Riet River group. Residual variance analysis performed on two-sample subsets of the Khoe-San group (Cape KS and Various KS) showed a higher level of heterogeneity in the Cape KS than seen in the Khoe-San from various other areas in southern Africa. MDA revealed that Khoe-San intra-sample variance is relatively high, with 44% of the sample (sexes pooled) classified into the Riet River group. The remaining individuals were classified (in decreasing order) into Bahutu (24%), Basuku (24%) and Sotho-Tswana (8%). Although the Khoe-San specimens are closest to the Riet River group, they are clearly not homogenous. Their high level of phenotypic diversity most likely originated from a complex population history involving many group interactions driven by social and political marginalization.     

Sequential Classification Based on Regression

Let us consider m general populations π₁, …,π_m. Each object belonging to these populations is represented by (p ± 1) characteristics x₁, x₂,…,x_p,y. A certain object, which is an element of one of the m general populations π₁,…,π_m has to be classified into the correct population. It will be assumed that knowledge of the value of the characteristic y would permit its correct classification, but that the observation of this characteristic is expensive, difficult or dangerous, as e.g. in medical applications. y is correlated with a set of p characteristics x₁,x₂,…,x_p, which are observed sequentially. The classification procedure is based on the division of the space of the observed value of characteristics x₁,x₂,…,x_p into nonintersecting areas determined so as to minimize the value of BAYES' risk given by equation (3).     

Prediction of macrofungal occurrence in Swedish beech forests from soil and litter variable models

The spatial distribution of 49 macrofungal species in Swedish beech forests was related to the statistical variation in 31 edaphic variables. In order to reduce the multicollinearity problem, the variables were transformed into eight principal components, PCs, which are used in two-group discriminant analysis (on absence/presence patterns) and multiple regression analysis (on number of fruit-bodies). The results suggested that base saturation and organic matter content are of outstanding importance. However, significant relationships were also found with other variables, i.e. Cd or Zn in soil and litter, soil nitrogen mineralization rate, and Na or S in litter. One interesting interpretation of the results is that fungi do not only respond to the main variables of a gradient (soil pH, organic mater, base saturation) but also to other variables. Attempts were made to interpret the PCs to characterize fungal occurrence from the models they formed.     

中国东北地带性顶极植被类型及其预测判别模型——动态地植物学说的继承与发展(Ⅰ)

本文根据刘慎谔的动态地植物学说原理,采用主成分分析法(PCA)和多组判别分析法(MGDA)研究了东北地区地带性顶极植被类型与气候指标的关系:1)以东北地区210个气象站的7个气象因子为变量,组成210×7矩阵,用PCA方法进行分类和排序,其结果明显划分7个地带性顶极植被类型,2)影响地带性顶极植被类型的形成和分布的气候因子,主要是热量和水分条件以及二者的组合状况;3)确定了7个地带性顶极植被类型的水热指数分布范围和特征;4)采用MGDA法建立了判别函数模型,预测了东北地区地带性顶极植被类型,其准确率可达90.32％。     

Temporal variation in prehistoric Nubian crania

Much of the earlier work on the prehistory of Sudanese Nubia has emphasized discontinuity between early Nubian populations. However, recent investigations suggest the converse - that a remarkable degree of cultural and biological continuity exists among indigenous Nubian groups, perhaps as far back as the Paleolithic. Thus, cultural and biological differences between Nubian populations can be most effectively perceived as the result of in situ evolutionary development. The present analysis has two major purposes: (1) to describe the morphological differences in the craniofacial complex between indigenous Nubian populations extending from the A-Group (c. 3,400 B.C.) through the Christian (c. 1,500 A.D.) horizons; and (2) to account for these differences within an evolutionary framework. The multiple discriminant analysis of radiographically derived variables revealed a trend from a substantially lower and more elongated cranial vault to a shorter and taller vault throughout the almost 5,000 year time span. Associated with this pattern was a tendency for the face to become more inferiorly-posteriorly located with respect to the vault in the latter groups. Finally, the masseter and temporalis muscles underwent a reduction and slight relocation through time. We speculate that this trend may be associated with behavioral changes associated with transition from a hunting and gathering to a totally agricultural subsistence pattern.     

Toward a Phylogenetic Classification of Primates Based on DNA Evidence Complemented by Fossil Evidence

A highly resolved primate cladogram based on DNA evidence is congruent with extant and fossil osteological evidence. A provisional primate classification based on this cladogram and the time scale provided by fossils and the model of local molecular clocks has all named taxa represent clades and assigns the same taxonomic rank to those clades of roughly equivalent age. Order Primates divides into Strepsirhini and Haplorhini. Strepsirhines divide into Lemuriformes and Loriformes, whereas haplorhines divide into Tarsiiformes and Anthropoidea. Within Anthropoidea when equivalent ranks are used for divisions within Platyrrhini and Catarrhini, Homininae divides into Hylobatini (common and siamang gibbon) and Hominini, and the latter divides into Pongina forPongo(orangutans) and Hominina forGorillaandHomo. Homoitself divides into the subgeneraH.(Homo) for humans andH.(Pan) for chimpanzees and bonobos. The differences between this provisional age related phylogenetic classification and current primate taxonomies are discussed.     

Relating new information to a previous vegetation classification: a case of discriminant coordinates analysis

Discriminant coordinates analysis is an adequate technique for analyzing the linear relationships between a number of new variates (i.e. environmental or functional attributes) and a set of vegetational attributes already summarized in the form of a classification. It displays the principal differences among classes in relation to the new variates considered. The procedure and its rationale are equivalent to a special case of principal components analysis.A case study on radiometer satellite data is presented. Two discriminant coordinates displayed the main differences in the seasonal dynamics of the NDVI (an index of standing green biomass) among broad phytogeo-graphic units in the Patagonia region. The first coordinate can be interpreted as an index of height and convexity of the NDVI seasonal curve. It suggests that the principal difference among regions was the total seasonal growth. The second coordinate represents a contrast that discriminated between two already detected patterns of seasonal NDVI curve.Abbreviations DC Discriminant Coordinate - NDVI Normalized Difference Vegetation Index     

Classification trees as an alternative to linear discriminant analysis

Linear discriminant analysis (LDA) is frequently used for classification/prediction problems in physical anthropology, but it is unusual to find examples where researchers consider the statistical limitations and assumptions required for this technique. In these instances, it is difficult to know whether the predictions are reliable. This paper considers a nonparametric alternative to predictive LDA: binary, recursive (or classification) trees. This approach has the advantage that data transformation is unnecessary, cases with missing predictor variables do not require special treatment, prediction success is not dependent on data meeting normality conditions or covariance homogeneity, and variable selection is intrinsic to the methodology. Here I compare the efficacy of classification trees with LDA, using typical morphometric data. With data from modern hominoids, the results show that both techniques perform nearly equally. With complete data sets, LDA may be a better choice, as is shown in this example, but with missing observations, classification trees perform outstandingly well, whereas commercial discriminant analysis programs do not predict classifications for cases with incompletely measured predictor variables and generally are not designed to address the problem of missing data. Testing of data prior to analysis is necessary, and classification trees are recommended either as a replacement for LDA or as a supplement whenever data do not meet relevant assumptions. It is highly recommended as an alternative to LDA whenever the data set contains important cases with missing predictor variables.     

The Empirical Bayes Classification Rules for Mixtures of Discrete and Continuous Variables

Let us consider a general population π. Each object belonging to the population π is characterized by a pair of correlated random vectors (X, Y ). Both X and Y may be mixtures of discrete and continuous random variables. It will be assumed that our population π consists of k groups π₁,….,πk, which depend on the value of the random vector Y. A certain object, which is an element of one of the k groups π₁, …, πk, has to be classified into the correct group. The knowledge of the value of the random vector Y would permit its correct classification, but the observation of this vector is difficult or dangerous and we must assign the individual on the basis of the observation of the random vector X . The classification procedure is based on randomized decision function δ* which minimizes the risk function i.e. Bayes decision function. We give also two empirical Bayes classification rules i.e. decision functions based on the sample from population π and having property that their risks converge to Bayes risk when the sample size increases.     

Comparative analysis of different impression techniques in relation to single tooth impression

It is of interest to compare the accuracy of three different impression techniques for a single tooth impression. We used 3 groups with 15 samples each in this study. Group 1: Putty and light body in a sectional stock tray; Group 2: Monophase and extra light body in a sectional stock tray; Group 3: Matrix impression technique. 15 impressions were taken of a prepared tooth on a typodont with each technique. The dimensions of the casts poured from these impression techniques were compared with the control typodont tooth. Data analysis shows that the matrix impression technique gave the best results in terms of dimensional study followed by monophase and extra light body impression technique and putty and light body impression technique gave the least accurate results. The results show that there is a statistically significant difference between the three impression techniques in terms of dimensional stability. Data analysis shows that the matrix impression technique gave the best results in terms of dimensional study followed by monophase and extra light body impression technique and putty and light body impression technique gave the least accurate results. The variations between the groups are within acceptable limits. Hence, it can be concluded that all the impression techniques will result in adequate dimensional stability and can be used in clinical scenarios.     

Structural Characterization and Chemical Classification of Some Bryophytes Found in Latvia

Bryophytes are the second largest taxonomic group in the plant kingdom; yet, studies conducted to better understand their chemical composition are rare. The aim of this study was to characterize the chemical composition of bryophytes common in Northern Europe by using elemental, spectral, and non‐destructive analytical methods, such as Fourier transform IR spectrometry (FT‐IR), solid‐phase ¹³C‐NMR spectrometry, and pyrolysis‐gas chromatography/mass spectrometry (Py‐GC/MS), for the purpose of investigating their chemotaxonomic relationships on the basis of chemical‐composition data. The results of all these analyses showed that bryophytes consist mainly of carbohydrates. Judging by FT‐IR spectra, the OH groups in combination of C? O groups were the most abundant groups. The ¹³C‐NMR spectra provided information on the presence of such compounds as phenolics and lipids. It was found that the amount of phenolic compounds in bryophytes is relatively small. This finding definitely confirmed the absence of lignin in the studied bryophytes. Cluster analysis was used to better understand differences in the chemical composition of bryophyte samples and to evaluate possible usage of these methods in the chemotaxonomy of bryophytes.     

Bias‐Corrected Diagonal Discriminant Rules for High‐Dimensional Classification

Summary Diagonal discriminant rules have been successfully used for high‐dimensional classification problems, but suffer from the serious drawback of biased discriminant scores. In this article, we propose improved diagonal discriminant rules with bias‐corrected discriminant scores for high‐dimensional classification. We show that the proposed discriminant scores dominate the standard ones under the quadratic loss function. Analytical results on why the bias‐corrected rules can potentially improve the predication accuracy are also provided. Finally, we demonstrate the improvement of the proposed rules over the original ones through extensive simulation studies and real case studies.     

Some Fossil Plants from Early Jurassic in Western Hubei With the Relative Problem Between Fossil Plants and Coal-Bearing

Coniopteris magnifica sp. nov., Ctenophyllum chenyuanense sp. nov., C. laxilobum sp. nov., Mironeura dakengensis Zhou, are derived from the Xiangxi Formation (s.s.), Western Hubei. According to the aspect and characteristic of the Xiangxi flora, author considers the Xiangxi Formation as Early Jurassic in age. In this paper, the relative problem between the coal-bearing and the fossil plants is briefly discussed also.     

IDQD算法预测人类蛋白质相互作用

蛋白质是一切生命活动的物质基础,研究蛋白质的相互作用有助于理解生物过程的分子机制,阐明疾病的分子机理。本文依据蛋白质序列组分特征,应用基于多样性增量的二次判别分析方法,对人类的1 963对蛋白质相互作用进行了预测。自洽检验的各项预测指标均在79%以上,且交叉检验的总精度也大于60%,表明本算法可以用于蛋白质相互作用预测。     

Characterizations of Some Discrete Distribution Models Arising in Pollen Studies

Characterizations are obtained for multinomial and multiple binominal mixtures. Examples are given when the beta distribution is used as the mixing distribution. Biological applications are indicated.     

Classifying genomic sequences by sequence feature analysis

Traditional sequence analysis depends on sequence alignment. In this study, we analyzed various functional regions of the human genome based on sequence features, including word frequency, dinucleotide relative abundance, and base-base correlation. We analyzed the human chromosome 22 and classified the upstream, exon, intron, downstream, and intergenic regions by principal component analysis and discriminant analysis of these features. The results show that we could classify the functional regions of genome based on sequence feature and discriminant analysis.     

Changes in the motility patterns of spermatozoa from the rabbit epididymis as assessed by computer-aided sperm motion analysis

Sperm maturation in the epididymis includes changes in their potential for motility that enables spermatozoa to reach the egg and penetrate its investments. The motility characteristics of spermatozoa from the testis, the epididymis, and vas deferens of the rabbit were investigated by computer-assisted sperm analysis (CASA). Various forms of motility were displayed by sperm from different regions of the epididymis released into incubation medium Testicular sperm were motile, although nonprogressive. The maximum percentage motility was expressed by sperm in the proximal cauda epididymidis, and forward progression was developed by spermatozoa from the distal caput. Once forward progression was established, the curvilinear velocity was about the same for sperm from all regions of the tract, whereas straight-line velocity increased between the mid-corpus and cauda and paralleled the decline in lateral displacement of the head. The maintenance of motility in vitro was best maintained by sperm from the distal regions of the tract although sperm from the distal caput maintained motility better than sperm from the proximal and midcorpus regions. Analysis of the motile sperm cells revealed several types of trajectories (“irregular,” “small circular,” “large circular and arcs,” “jagged” and “straight-line”) that were analyzed by discriminant analysis using the variables generated by CASA. Accuracy of classification varied from 70% to 96%, depending on the type of track. The classification function was then applied to the changes that occurred during incubation and showed that irregular trajectories gave way to small and then large circular tracks and progressive forms as sperm matured. © 1996 Wiley-Liss, Inc.