Multivariate analysis in biological anthropology: Some considerations

The relation between modern multivariate statistical analysis and common objectives in biological anthropology is discussed. Many formal statistical assumptions should be satisfied to fully justify multi-variate analysis, but rarely are. Their failure does not have as adverse an effect upon scientific research as some procedural errors in research design. These include the treatment of single specimens as if they are samples, and the failure to separate considerations of size and shape. The superiority of elaborate multivariate distances over simpler quantitative techniques, inferred from the former's consideration of trait intercorrelations, is unwarranted from both theoretical and practical aspects. Based on these points and several comparative examples of analyses, it is argued that simpler, non-statistical approaches such as those of the school of numerical taxonomy have much to offer primato-logical studies. Classic multivariate statistics, while useful for studying closely similar living populations, are considerably more limited in usefulness and significance for paleoanthropological studies.     

李园桃蚜和草间小黑蛛种群空间格局的地学统计学研究

利用地学统计学的原理和方法分析了李园桃蚜种群和草间小黑蛛种群的空间结构和时间相关性.结果表明,桃蚜种群6月27日和11月22日此两次的半变异函数拟合模型为直线,表明此两次两种空间分布为均匀分布或随机分布,其余9次半变异函数拟合模型均为球形,表明此9次李园桃蚜种群的空间分布是聚集分布,变程RSD(m)为4.173903～34.7837.草间小黑蛛空间格局5月21日、5月31日及10月19日、11月22日4次半变异函数拟合模型为直线,表明此4次种群的空间分布为均匀分布或随机分布,其余8次半变异函数拟合模型均为球形,表明此8次李园草间小黑蛛种群的空间分布是聚集分布,变程RSD(m)为2.3169～42.00711,表明草间小黑蛛种群对桃蚜种群在空间位置上具有追随关系,对其种群数量的控制有较大作用.     

基于地统计学丰林自然保护区森林生物量估测及空间格局分析

摘要： 基于丰林保护区1997年样地调查数据,根据一元生物量估测模型,计算样地生物量,在此基础上,利用ArcGIS地统计插值方法得到整个研究区森林生物量分布,并从林分结构（林型、林龄组）和地形因子（海拔、坡度、坡向）两个方面对保护区森林生物量空间格局进行了分析。结果表明,利用地统计插值得到区域水平的森林生物量是可行的,保护区森林平均生物量水平为171.5t/hm2,总生物量为3.08Tg(1Tg=1012g);不同林分结构（林型、林龄组）有不同的生物量水平;地形因子与生物量有显著的相关性,并得到它们之间的回归方程,为保护区森林生态系统的可持续经营提供了科学依据。     

Living with observational data in biological anthropology

The establishment of cause and effect relationships is a fundamental objective of scientific research. Many lines of evidence can be used to make cause–effect inferences. When statistical data are involved, alternative explanations for the statistical relationship need to be ruled out. These include chance (apparent patterns due to random factors), confounding effects (a relationship between two variables because they are each associated with an unmeasured third variable), and sampling bias (effects due to preexisting properties of compared groups). The gold standard for managing these issues is a controlled randomized experiment. In disciplines such as biological anthropology, where controlled experiments are not possible for many research questions, causal inferences are made from observational data. Methods that statisticians recommend for this difficult objective have not been widely adopted in the biological anthropology literature. Issues involved in using statistics to make valid causal inferences from observational data are discussed.     

Understanding racism in physical (biological) anthropology

The mainstream of American physical anthropology began as racist and eugenical science that defended slavery, restricted “non-Nordic” immigration, and justified Jim Crow segregation. After World War II, the field became more anti-racial than anti-racist. It has continued as a study of natural influences on human variation and thus continues to evade the social histories of inequitable biological variation. Also reflecting its occupancy of white space, biological anthropology continues to deny its own racist history and marginalizes the contributions of Blacks. Critical disciplinary history and a shift toward biocultural studies might begin an anti-racist human biology.     

Testing type II error rates in biological anthropology

This paper presents a look at the underused procedure of testing for Type II errors when "negative" results are encountered during research. It recommends setting a statistical alternative hypothesis based on anthropologically derived information and calculating the probability of committing this type of error. In this manner, the process is similar to that used for testing Type I errors, which is clarified by examples from the literature. It is hoped that researchers will use the information presented here as a means of attaching levels of probability to acceptance of null hypotheses.     

A Practical Examination of the Use of Geostatistics in the Remediation of a Site with a Complex Metal Contamination History

Targeted remediation strategies offer the potential to treat only those areas where contamination exceeds predefined threshold levels. We used geostatistical techniques to characterize spatial distribution of heavy metals across a contaminated site, with the aim of delineating the contaminants, which is essential for successful implementation of targeted remediation strategies. Samples collected from three depths, 0–20 cm, 20–40 cm and 40–60 cm at 50 sample locations, were analyzed for As, Sb, Hg, Pb, Cd and Cu contents. The geostatistical analysis of this data enabled the identification of a number of contamination hotspots and trends. The visual interpretation of the data was supported by the statistical analysis in the form of Spearman's rank correlation coefficient. Additionally, classical statistics, based on the central limit theorem, showed that, in terms of obtaining the true mean for each of the contaminants within acceptable limits of precision, the site has been more than adequately sampled.It has been demonstrated that kriging can offer the potential to map the spatial distribution of contaminants. However, the possibility of an undetected hotspot remains, even when probabilistic modelling and a secondary phase of validatory sampling are employed. This together with the large number of samples required may preclude the commercial use of geostatistics in the remediation of contaminated land.     

基于神经网络模型和地统计学方法的土壤养分空间分布预测

采用径向基函数神经网络模型与普通克里格法相结合的方法,预测川中丘陵区县域尺度土壤养分(有机质和全氮)的空间分布,并与普通克里格法和回归克里格法进行比较.结果表明：各方法对研究区土壤养分的预测结果相似.与多元回归模型相比,神经网络模型对验证样点土壤有机质和全氮的预测值与样点实测值的相关系数分别提高了12.3%和16.5%,表明神经网络模型能更准确地捕捉土壤养分与定量环境因子间的复杂关系.对469个验证样点预测结果的误差分析表明,神经网络模型与普通克里格法相结合的方法对土壤有机质和全氮预测结果的平均绝对误差、平均相对误差、均方根误差较普通克里格法分别降低了6.9%、7.4%、5.1%和4.9%、6.1%、4.6%,降低幅度达到极显著水平(P<0.01);与回归克里格法相比则分别降低了2.4%、2.6%、1.8%和2.1%、2.8%、2.2%,降低幅度达显著水平(P<0.05).     

Spatial Analysis of Twaite Shad,Alosa fallax (Lacepède, 1803), in the Southern North Sea: Application of Non‐Linear Geostatistics as a Tool to Search for Special Areas of Conservation

This study aims to evaluate the suitability of non‐linear geostatistics and indicator kriging (IK) as a tool in environmental impact assessment and nature conservation, in particular to search for potential Special Areas of Conservation (SAC) for the endangered fish species twaite shad, Alosa fallax (Lacepède , 1803) within the German Exclusive Economical Zone (EEZ) of the North Sea. To analyse the spatial distribution of this fish species, data on standardised biomass index (catch per unit effort, c.p.u.e., kg × 30 min^–1) from 1996 to 2001 were used, regarding the third and fourth quarters of each year, respectively. Thereby we assume that the spatial distribution can be described as a time‐invariant process. This assumption is supported by information on annual sampling effort, allocation of hauls and spatial distribution of the positive catches. All indicator variograms obtained for different c.p.u.e. cut‐off values displayed distinct spatial structures, clearly indicating that the indicator variables were spatially autocorrelated. Gaussian models were fitted by least‐squares methods and were evaluated with a goodness‐of‐fit statistic. Subsequently, IK was employed to estimate the probability of exceeding the c.p.u.e. cut‐off values for the twaite shad in the investigation area. These were highest in the Weser‐ and Elbe‐estuary, probably because of migrations of twaite shad to and from estuaries at the time of investigation due to spawning, while within the German EEZ of the North Sea no such areas with increased probabilities could be discerned. Thus, although available data did not allow to identify and implement any SAC in the German EEZ, the methods employed here can be regarded as a promising management tool in biological conservation issues. (© 2004 WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheim)     

The continuing misuse of null hypothesis significance testing in biological anthropology

There is over 60 years of discussion in the statistical literature concerning the misuse and limitations of null hypothesis significance tests (NHST). Based on the prevalence of NHST in biological anthropology research, it appears that the discipline generally is unaware of these concerns. The p values used in NHST usually are interpreted incorrectly. A p value indicates the probability of the data given the null hypothesis. It should not be interpreted as the probability that the null hypothesis is true or as evidence for or against any specific alternative to the null hypothesis. P values are a function of both the sample size and the effect size, and therefore do not indicate whether the effect observed in the study is important, large, or small. P values have poor replicability in repeated experiments. The distribution of p values is continuous and varies from 0 to 1.0. The use of a cut‐off, generally p ≤ 0.05, to separate significant from nonsignificant results, is an arbitrary dichotomization of continuous variation. In 2016, the American Statistical Association issued a statement of principles regarding the misinterpretation of NHST, the first time it has done so regarding a specific statistical procedure in its 180‐year history. Effect sizes and confidence intervals, which can be calculated for any data used to calculate p values, provide more and better information about tested hypotheses than p values and NHST.     

Skeletal biological distance studies in American physical anthropology: recent trends

Biological distance analysis, the dominant type of skeletal biological research during the 19th century, has become less visible in recent years. Although the proportion of American Journal of Physical Anthropology articles and published abstracts focusing on biodistance has remained fairly constant over the three decades between 1955 and 1985, the proportion of biodistance contributions relative to other skeletal biology studies has decreased. Emphasis in skeletal biology has shifted from the analysis of biological variation to investigations of health and diet, and within biodistance studies methodological issues have assumed prominence over purely analytical approaches. This paper investigates trends in biological distance analysis through a survey of articles and meetings abstracts published in the American Journal of Physical Anthropology from 1955 to 1985. The survey provides the historical context for five symposium papers on skeletal biological distance presented at the 1986 meeting of the American Association of Physical Anthropologists.     

江西兴国水土流失治理区土壤有机质动态变化

在ArcGIS8.1软件系统平台上,用普通克立格和概率克立格等多种方法研究潋水河流域土壤有机质含量的动态变化特征。结果表明,潋水河流域106个样点的土壤有机质平均含量增加,由1981年的18.16±7.23g/kg增加到2002年的19.14±11.25g/kg;2002年土壤有机质含量为(30.0～40.0g/kg)、(20.0～30.0g/kg)级地的面积扩大,所占流域面积比分别较1981年增加11.38%和28.54%。近20年来该流域内水田、旱地和林地的土壤有机质平均增加量分别为2.3g/kg、3.5g/kg和3.1g/kg,坡度≤2°、2～6°、6～15°、15～25°和>25°的土壤有机质平均增加量分别为1.8g/kg、2.6g/kg、3.3g/kg、3.6g/kg和4.0g/kg。结合概率克立格法和加权平均法探讨了<10.0g/kg含量水平下区域土壤有机质的概率分布特征,其几何平均概率由1981年的0.2008下降到2002年的0.1503。     

Statistical opportunities for analyzing spatial and temporal heterogeneity of field soils

Statistical techniques for analyzing data in the agricultural sciences have traditionally followed the pioneering efforts of R.A. Fisher who assumed that observations in the field were independent and identically distributed. Such techniques, proven useful in the past and still being used today for comparing the merits of different management practices or different treatments, are presently giving way to additional methods that are based upon observations being spatially or temporally correlated. It is physically more sensible to expect soil attributes to be correlated when they are measured at adjacent points in space or time. Spatially repetitious patterns of soil attributes for physical and biological processes occurring at distances of a few molecules to those of kilometers are also expected. Opportunities to use geostatistics, time series analyses, state-space models, spectral analyses of variance, lagged regression models and other alternative techniques for analyzing multidimensional random fields are available to enhance the understanding of agro-ecosystems. Approaches to modeling and fitting data using stochastic partial differential equations and scaling techniques also help reveal the underlying processes occurring in field soils. Inclusion of these alternatives in the development of an agro-ecological technology leads to improved sampling designs to better entire management units, rather than ascertaining the impact of particular, sometimes arbitrary treatments applied to a set of small plots using analysis of variance methods.