农残水平测试中数据多态性分析及指定值估计研究

对全国农残水平测试中毒死蜱、氯氰菊酯数据进行统计分析,在数据统计分布特征研究基础上,使用内核密度估计进行数据多态性分析,使用bootstrap模拟取样法对数据样本值重复取样,以获得稳健的水平测试样品待测物含量代表值估计、标准误差及置信区间描述,证明以bootstrap模拟取样法获取的均值与标准偏差作为有限单次样本代表值是合理、有效的,解决了四分位稳健统计方法对非正态多态分布代表值估计不稳定问题及取样理论中取样样本数限制的瓶颈,为能力验证计划指定值的获取提供了一种新方法。     

Bootstrap method for the estimation of measurement uncertainty in spotted dual-color DNA microarrays

DNA microarrays permit the measurement of gene expression across the entire genome of an organism, but the quality of the thousands of measurements is highly variable. For spotted dual-color microarrays the situation is complicated by the use of ratio measurements. Studies have shown that measurement errors can be described by multiplicative and additive terms, with the latter dominating for low-intensity measurements. In this work, a measurement-error model is presented that partitions the variance into general experimental sources and sources associated with the calculation of the ratio from noisy pixel data. The former is described by a proportional (multiplicative) structure, while the latter is estimated using a statistical bootstrap method. The model is validated using simulations and three experimental data sets. Monte-Carlo fits of the model to data from duplicate experiments are excellent, but suggest that the bootstrap estimates, while proportionately correct, may be underestimated. The bootstrap standard error estimates are particularly useful in determining the reliability of individual microarray spots without the need for replicate spotting. This information can be used in screening or weighting the measurements.     

Reference values versus consensus values: a reaction to the article of Baldan et al.

In a recent article Baldan et al. concluded that reference values can be used in a proficiency test as assigned values and that this does not increase the cost of the proficiency test. They feel that the values found during an homogeneity test could be used as reference values. In this article, it is argued that the conclusions of Baldan et al. have only a very limited validity. Due to the difference in goals, homogeneity data cannot be used for the determination of reference values without a drastic change in set-up. And in practice, in many fields of application, the situation is quite different than Baldan et al. suggest. Thus in many proficiency testing studies it is not technically possible to use reference values and in cases where it is possible, the costs will increase significantly if reference values are used instead of consensus values.     

鸡蛋中氟虫腈砜能力验证样品单元内与单元间均匀性评价案例与模型分析

对鸡蛋中氟虫腈砜能力验证样品进行单元内均匀性和单元间均匀性评价。对能力验证涉及的检测方法进行方法学考察,按照预设的模型,在单元内和单元间取样检测。使用单元内子样结果均方差和方法重复性均方差构建单因素方差分析模型,完成了单元内均匀性评价。对单元间和单元内均匀性评价的方差分析模型中组间和组内方差的来源及代表性进行了讨论。结果表明鸡蛋中氟虫腈砜样品的单元内均匀性和单元间均匀性满足要求。开展单元内均匀性评价有利于掌握能力验证方法性能,确认检测最小取样量,识别不均匀性来源,增加单元间均匀性评价的可靠性。建立的单元内均匀性评价模型克服了标准模型中多次转化测量数据难以获得的问题,可在各类能力验证项目中推广应用。     

用经验模型评估环境样品测量不确定度

利用水样、土壤和沉积物标准样品定值数据,建立了评估环境样品测量结果不确定度的经验模型。讨论了判断模型质量的指标。用建立的经验模型估算了实际标样和能力验证数据不确定度,并与实测结果进行了比较。探讨了利用本模型计算的相对标准偏差允许限用于实验室内部质量管理与控制的可行性。经验模型能帮助客户判断送检样品检测结果在临界值时能否满足相关要求。     

Quality issues in proficiency testing

 Proficiency testing is a means of assessing the ability of laboratories to competently perform specific tests and/or measurements. It supplements a laboratory's own internal quality control procedure by providing an additional external audit of their testing capability and provides laboratories with a sound basis for continuous improvement. It is also a means towards achieving comparability of measurement between laboratories. Participation is one of the few ways in which a laboratory can compare its performance with that of other laboratories. Good performance in proficiency testing schemes provides independent evidence and hence reassurance to the laboratory and its clients that its procedures, test methods and other laboratory operations are under control. For test results to have any credibility, they must be traceable to a standard of measurement, preferably in terms of SI units, and must be accompanied by a statement of uncertainty. Analytical chemists are coming to realise that this is just as true in their field as it is for physical measurements, and applies equally to proficiency testing results and laboratory test reports. Recent approaches toward ensuring the quality and comparability of proficiency testing schemes and the means of evaluating proficiency test results are described. These have led to the drafting of guidelines and subsequently to the development of international requirements for the competence of scheme providers. Received: 2 January 1999 · Accepted: 7 April 1999     

The comparison of parametric and nonparametric bootstrap methods for reference interval computation in small sample size groups

According to the IFCC, to determine the population-based reference interval (RI) of a test, 120 reference individuals are required. However, for some age groups such as newborns and preterm babies, it is difficult to obtain enough reference individuals. In this study, we consider both parametric and nonparametric bootstrap methods for estimating RIs and the associated confidence intervals (CIs) in small sample size groups. We used data from four different tests [glucose, creatinine, blood urea nitrogen (BUN), and triglycerides], each in 120 individuals, to calculate the RIs and the associated CIs using nonparametric and parametric approaches. Also for each test, we selected small groups (m = 20, 30,…, 120) from among the 120 individuals and applied parametric and nonparametric bootstrap methods. The glucose and creatinine data were normally distributed, and the parametric bootstrap method provided more precise RIs (i.e., the associated CIs were narrower). In contrast, the BUN and triglyceride data were not normally distributed, and the nonparametric bootstrap method provided better results. With the bootstrap methods, the RIs and CIs of small groups were similar to those of the 120 subjects required for the nonparametric method, with a slight loss of precision. For original data with normal or close to normal distribution, the parametric bootstrap approach should be used, instead of nonparametric methods. For original data that deviate significantly from a normal distribution, the nonparametric bootstrap should be applied. Using the bootstrap methods, fewer samples are required for computing RIs, with only a slightly increased uncertainty around the end points.     

水平测试样品的均匀性保证

为确保水平测试样品的均匀性，文中阐述了水平测试、样品制备、均匀性检验的取样数量、取样方式、最小取样量、测量方法和统计方法，重点介绍了均匀性检验的统计方法。     

Self-interaction error in density functional theory: a mean-field correction for molecules and large systems

Corrections to the self-interaction error which is rooted in all standard exchange-correlation functionals in the density functional theory (DFT) have become the object of an increasing interest. After an introduction reminding the origin of the self-interaction error in the DFT formalism, and a brief review of the self-interaction free approximations, we present a simple, yet effective, self-consistent method to correct this error. The model is based on an average density self-interaction correction (ADSIC), where both exchange and Coulomb contributions are screened by a fraction of the electron density. The ansatz on which the method is built makes it particularly appealing, due to its simplicity and its favorable scaling with the size of the system. We have tested the ADSIC approach on one of the classical pathological problem for density functional theory: the direct estimation of the ionization potential from orbital eigenvalues. A large set of different chemical systems, ranging from simple atoms to large fullerenes, has been considered as test cases. Our results show that the ADSIC approach provides good numerical values for all the molecular systems, the agreement with the experimental values increasing, due to its average ansatz, with the size (conjugation) of the systems.     

An alternative statistical approach for interlaboratory comparison data evaluation

Interlaboratory comparisons are an essential component of method validation, laboratory proficiency and equivalency evaluation, and standard reference material certification. The reliability of the results from interlaboratory comparison largely depends upon analyzing the data with appropriate statistical methods. Intercomparison data are often found to be non-normally distributed as a result of sample heterogeneity, uneven laboratory variance, and methodology bias. The statistical methods that require data normality are inappropriate for analyzing such skewed data. Instead of using data transformation or non-parametric methods, an alternative method which sets aside the assumption of data normality is utilized in the certification of new National Institute of Standards and Technology (NIST) Ocean Sediment Standard Reference Material (SRM-4357). It first determines the best-fit distribution for the data, then calculates appropriate distributional mean and tolerance limits, and finally estimates the uncertainties for the derived statistics by bootstrap analysis. The method was applied to evaluate the data from the SRM intercomparison, and revealed homogeneity for natural radionuclides and inhomogeneity for anthropogenic radionuclides in the SRM. It was found that the data of natural radionuclides in the SRM are normally distributed. In contrast, the data of anthropogenic radionuclides, such as ⁹⁰Sr, ¹³⁷Cs, ²³⁸Pu, and ^(239+240)Pu, are best fitted by Weibull distributions. The difference on data distributions for the two types of radionuclides is believed to be related to "hot" particles in the SRM. By determining the best-fit data distribution and applying bootstrap analysis, more reliable and realistic massic activity (Bq·kg^-1) for anthropogenic radionuclides were certified in comparison to those obtained using data transformation and nonparametric methods. Although the developed method is computationally intensive, it provides a straightforward, rigorous procedure for computing the statistics that would otherwise be difficult to obtain when the data distribution form is complicated. With the help of advanced personal computers and use of the DataPlot software from NIST, this method becomes very practical and has enhanced interlaboratory comparison data studies and certification of the NIST standard reference materials.     

An error model for evaluation and interpretation of proficiency testing

Data from proficiency testing can be used to increase our knowledge of the performance of populations of laboratories, individual laboratories and different measurement methods. To support the evaluation and interpretation of results from proficiency testing an error model containing different random and systematic components is presented. From a single round of a proficiency testing scheme the total variation in a population of laboratories can be estimated. With results from several rounds the random variation can be separated into a laboratory and time component and for individual laboratories it is then also possible to evaluate stability and bias in relation to the population mean. By comparing results from laboratories using different methods systematic differences between methods may be indicated. By using results from several rounds a systematic difference can be partitioned into two components: a common systematic difference, possibly depending on the level, and a sample-specific component. It is essential to distinguish between these two components as the former may be eliminated by a correction while the latter must be treated as a random component in the evaluation of uncertainty. Received: 20 November 2000 Accepted: 3 January 2001     

Determination of Assigned Values for Cadmium,Cobalt and Manganese in Drinking Water Proficiency Testing

In proficiency tests the selection of an appropriate assigned value is one of the most critical points. Determination of the assigned value for proficiency test can be done in 2 ways: based on reference value and consensus value. The use of such a consensus value as an assigned value is a commonplace in proficiency testing, because there is seldom at present a cost effective alternative. However, the consensus value has a weakness in that it could be significantly different from the true value due largely inexperienced laboratories. Therefore in this work, the reference values were used as the assigned values for all analytes of interest. The reference values in spiked drinking water samples were produced by the Metrology in Chemistry Laboratory of Research Center for Chemistry - Indonesian Institute of Sciences (RCChem-LIPI) with traceable to SI units through standard solutions from the National Institute Standard and Technology, USA. The reference values of cobalt and manganese were obtained by measurement using two from three comparable methods of Graphite Furnace-Atomic Absorption Spectrometry (GF-AAS), Inductively Coupled Plasma-Optical Emission Spectrometry (ICP-OES) and Inductively Coupled Plasma-Mass Spectrometry (ICP-MS) while that for cadmium was obtained by a primary method of ICP-Isotope Dilution Mass Spectrometry (ICP-IDMS).The obtained reference values were used to evaluate the laboratory performance result in a proficiency testing scheme of cadmium, cobalt and manganese in drinking water which was provided in 2014. All fifty nine laboratories reported cadmium and cobalt at low concentration levels which were about more than 82% showed satisfactory performance results. Similarly, the results of manganese were also comparable at high level concentrations.     

A bootstrap‐based method for optimal design of experiments

Bootstrapping can be used for the estimation of parameter variances, and it is straightforward to be implemented but computationally demanding compared with other methods for parameter error estimation. It is not bound to any restrictions such as the distribution of measurement errors. And because of the possible asymmetry of the probability densities of the parameters, the parameter estimation errors acquired by bootstrapping are likely to be more accurate. In this work the feasibility of a bootstrap‐based method for optimal experimental design was evaluated for the Peleg model. The optimal design was performed, based on the Cramér‐Rao lower bound as a benchmark. Afterwards, the optimal design was calculated based on the bootstrap method. It is demonstrated that a bootstrap‐based optimal design of experiments will give comparable results with the Cramér‐Rao lower bound optimal designs, however with slightly different measurement points in time. If the parameter errors obtained from both optimal experimental designs are compared, they deviate for the 2 methods on average by 1.5%. Bootstrapping can be used for problems, which cannot be solved using Cramér‐Rao lower bound because of necessary but invalid assumptions. However, the benefits of the bootstrap method come at the cost of a significant increase in computational effort. Under similar conditions, the computation time for a bootstrap‐based optimal design was 25 minutes compared with 5 seconds when using the Cramér‐Rao lower bound method. As computers get faster and faster over time, the increase in computational demand will probably become less relevant in the future.     

Confidence intervals for calibration with neural networks

Based on neural network calibration the confidence intervals of aromaticity determination from infrared reflectance spectra of raw brown coals were estimated by means of the bootstrap method, a simplified Monte Carlo Simulation. The standard deviations and the confidence intervals were estimated to characterise the analysis error.It is shown that confidence intervals of non-linear analysis methods like Back Propagation Neural Networks (BPNN) can be estimated by the bootstrap method. The estimated confidence intervals of the calibration confirm the analysis by BPNN.     

Uncertainty evaluation in proficiency testing: state-of-the-art, challenges, and perspectives

The evaluation of measurement uncertainty, and that of uncertainty statements of participating laboratories will be a challenge to be met in the coming years. The publication of ISO 17025 has led to the situation that testing laboratories should, to a certain extent, meet the same requirements regarding measurement uncertainty and traceability. As a consequence, proficiency test organizers should deal with the issues measurement uncertainty and traceability as well. Two common statistical models used in proficiency testing are revisited to explore the options to include the evaluation of the measurement uncertainty of the PTRV (proficiency test reference value). Furthermore, the use of this PTRV and its uncertainty estimate for assessing the uncertainty statements of the participants for the two models will be discussed. It is concluded that in analogy to Key Comparisons it is feasible to implement proficiency tests in such a way, that the new requirements can be met. Received: 29 September 2000 Accepted: 3 December 2000     

Reliability of proficiency test results for metals and phthalates in plastics

In a recent article it was concluded that the Horwitz curve could not be used for evaluation of results from analysis of plastics. This conclusion was based on 15 different proficiency tests of which 11 were organized by the Institute for Interlaboratory Studies. The authors suggest that part of the poor interlaboratory reproducibility can be explained by the inhomogeneity of consumer plastic products. Also, the lack of standard methods has been mentioned as problematic. The value of the iis data sets used by the authors is discussed in this paper. More recent data are also investigated to determine whether the situation with regard to analysis of plastics is as bad as suggested by Ritter and Meyer.     

Acrylamide analysis: assessment of results from six rounds of Food Analysis Performance Assessment Scheme (FAPAS) proficiency testing

Six proficiency tests have now been completed in an ongoing program of the UK Food Analysis Performance Assessment Scheme (FAPAS) for the analysis of acrylamide in a range of food matrixes. Homogeneous test material samples were requested by laboratories throughout the world, with 29 to 45 submitting results for each test. Results were analyzed by appropriate statistical procedures, and z-scores were awarded for reported values. In the absence of both legislation and collaborative trial data, the target standard deviation was derived from the Horwitz equation, although it is acknowledged that there is a need to establish a "fit for purpose" target standard deviation specifically for acrylamide analysis. Participants were encouraged to use the analytical method routinely used in their own laboratory and to provide details of their procedure. Close examination of the data submitted indicates that performance is generally acceptable in terms of accuracy. There is no significant difference between results submitted by gas chromatography and liquid chromatography (GC and LC) methods, and no method dependency on the use of internal standards or sample size. However, choice of extraction solvent may be important, with indications that plain water is an acceptable extraction method. There is evidence from the most recent test that direct (underivatized) GC methodology may present problems, but more data are required and this aspect will be monitored in the continuing proficiency testing program.     

Nonparametric assessment of comparability of analytical results obtained in proficiency testing based on a metrological approach

A nonparametric sign test is implemented for assessment of comparability of proficiency testing (PT) results when their distribution differs from the normal or other known distribution. It allows testing the null hypothesis about insignificance of the bias of median of results obtained in PT from the traceable certified value of the reference material used in PT as test items, i.e., the hypothesis stating that comparability of the PT results is successful. Probability of type I error of rejecting the null hypothesis when it is true, and probability of type II error of it not rejecting when it is false (the alternative hypothesis about unsuccessful comparability is true) are considered. The test can be helpful for PT providers and laboratory accreditation bodies in analysis of PT results when the comparability criterion developed for a normal results distribution (Accred. Qual. Assur. 10:466–470) is not applicable.     

The variance of a consensus

In proficiency tests the consensus of the participants' results is often used as the assigned value to calculate z-scores. Where the consensus is quantified as the robust mean of n results, the standard error of the assigned value is often taken to be , where is the robust standard deviation estimated from the same data ¹ . As some of the results are downweighted in robust estimation, is too large a denominator, so that tends to have a somewhat low bias. This bias is shown to be inconsequential for proficiency testing purposes. However, an unbiased estimate can be obtained by using the bootstrap.

---