HOW TO USE GRAPHS TO DIAGNOSE AND DEAL WITH BAD EXPERIMENTAL DATA

机译：如何使用图表对不良实验数据进行诊断和处理

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

This talk deals with thorny issues that confront every experimenter - how to deal with individual results that do not appear to fit with the rest of the data. It provides graphical tools that will help experimenters properly diagnose what's really wrong with their data - damaging outliers and/or a need for response transformation. The trick is to maintain a reasonable balance between two types of errors: 1. Deleting data that vary only due to common causes, thus introducing bias to the conclusions. 2. Not detecting true outliers that occur due to special causes. Such outliers can obscure real effects or lead to false conclusions. Furthermore, an opportunity may be lost to learn about preventable causes for failure or reproducible conditions leading to breakthrough improvements (making discoveries more or less by-accident). Attendees will see two real-life data sets that don't reveal their secrets at first glance. However, with the aid of various diagnostic plots (readily available in off-the-shelf statistical software), it becomes much clearer what needs to be done. Armed with this knowledge, quality professionals will be much more likely to draw the proper conclusions from experiments that produce bad (discrepant) data.

机译：本演讲涉及每个实验者面临的棘手问题-如何处理似乎与其余数据不符的单个结果。它提供了图形化工具，可以帮助实验者正确诊断数据的真正错误-损坏异常值和/或需要响应转换。诀窍是要在两种类型的错误之间保持合理的平衡：1.删除仅由于常见原因而变化的数据，从而使结论有偏差。 2.未检测到由于特殊原因而发生的真实异常值。这样的异常值可能掩盖真实的效果或导致错误的结论。此外，可能会失去机会来学习可预防的失败原因或可重现的条件，从而导致突破性的改进（或多或少是偶然发现）。与会者将看到两个真实的数据集，这些数据集乍一看并没有揭示他们的秘密。但是，借助各种诊断图（现成的统计软件中已有），变得更清楚需要做什么。有了这些知识，高质量的专业人员将更有可能从产生错误数据的实验中得出正确的结论。

著录项

来源
《American Society for Quality (ASQ)'s 57th Annual Quality Congress May 19-21, 2003 Kansas City, Missouri》|2003年|p.477-487|共11页
会议地点 Kansas City MO(US)
作者
Mark J. Anderson; Patrick J. Whitcomb;
展开▼
作者单位

Stat-Ease, Inc. Minneapolis, MN 55413;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类经济计划与管理;
关键词

相似文献

外文文献
中文文献
专利

1. Using Graphical Diagnostics to Deal With Bad Data [J] . Mark J. Anderson, Patrick J. Whitcomb Quality engineering . 2007,第2期

机译：使用图形诊断来处理不良数据
2. Using graphical diagnostics to deal with bad data [J] . Mark J. Anderson, Patrick J. Whitcomb Quality Control and Applied Statistics . 2007,第6期

机译：使用图形诊断来处理不良数据
3. The Good, the Bad, and the Data: Shane the Lone Ethnographer's Basic Guide to Qualitative Data Analysis [J] . Elizabeth Losh Technical communication quarterly . 2020,第3期

机译：好的，坏的和数据：Shane Lone Lennographer的定性数据分析基本指南
4. HOW TO USE GRAPHS TO DIAGNOSE AND DEAL WITH BAD EXPERIMENTAL DATA [C] . Mark J. Anderson, Patrick J. Whitcomb ASQ's Annual Quality Congress . 2003

机译：如何使用图形来诊断和处理不良的实验数据
5. Interactive graphics, graphical user interfaces and software interfaces for the analysis of biological experimental data and networks [D] . Lawrence, Michael 2008

机译：交互式图形，图形用户界面和软件界面，用于分析生物实验数据和网络
6. The Comparison between the Echocardiographic Data to the Cardiac Catheterization Data on the Diagnosis Treatment and Follow-Up in Patients Diagnosed as Pulmonary Valve Stenosis [O] . Do Hoon Kim, Su-Jin Park, Jo Won Jung, 2013

机译：超声心动图数据与心脏导管检查数据在诊断为肺动脉瓣狭窄的患者的诊断治疗和随访中的比较
7. : "This paper deals with the functionality of the flaked stone assemblages from several Neolithic sites of the NE of the Iberian Peninsula. The chronological framework ranges from the mid-6th to the mid-4th millennium cal. BCE, which corresponds to the Early and Middle Neolithic. This long period ranges from the arrival of the first farming communities in the Iberian Peninsula, around 5600-5500 cal. BCE, to 3600-3500 cal. BCE, two millennia later, when Neolithic communities had stably occupied most of the available territory, from the mountainous areas of the Pyrenees to the coastal areas of the Mediterranean.In this context, the NE of the Iberian Peninsula is one of the areas where a major number of use-wear analyses have been carried out, especially for what concerns the Neolithic period. This is mainly due to the interest shown by the directors of the excavations and by the Spanish use-wear specialists as well; both participated and cooperated in order to enlarge the number of contexts studied, making the NE of the Iberian Peninsula one of the areas of Europe with the largest number of ‘functional studies’. As a result, today we have a reliable picture of the type of lithic tools used by the first farming groups, how they were used, and which needs they were satisfying.The methodology employed for this type of analysis is today broadly shared by most use-wear specialists. A stereoscopic microscope is used together with a reflected-light microscope for the analysis of the archaeological specimens. Afterwards, the observed use-wear traces are compared with the traces from experimental tools. This study primarily made use of the tools preserved at the ‘Traceoteque’ of the Institución Milà y Fontanals of the CSIC of Barcelona.This paper presents the results obtained for the different types of analysed sites and the relative lithic assemblages. In this way, tools from different contexts are compared: open-air sites, caves and rock-shelters, pit-sites, burials, and mining sites. Such a diversity of contexts allowed for the exploration of the existence of recurrences and differences in the functionality of the lithic tools from one site to another. The results obtained have also provided information on some aspects related to the economic processes carried out at the different sites, caves, rock-shelters and open-air contexts. It has been possible to gain fresh data on the types of tasks carried out and their relative importance for each site, their relation with the geographical and environmental context and the natural resources available there. In addition, analysing tools recovered from burials – mainly individual inhumations – provided information on the relationships between the buried individuals and the working tools, in particular exploring the relationships between sex and age patterns and the types of tools deposited as goods.In conclusion, use-wear analysis allowed for the exploration of a variety of issues; from technical aspects related to the production and management of the lithic resources to social aspects related to the subsistence activities and the individuals that carried them out." [O] . Gibaja Bao, Juan Francisco, Mazzucco, Niccolo 2015

机译：：“本文研究了伊比利亚半岛东北部几个新石器时代遗址的片状石材组合的功能。时间框架从公元前6世纪中叶到4世纪中叶，分别对应于早期和早期。新石器时代中期，这段时间的长短是从伊比利亚半岛的第一个农业社区到来，大约在公元前5600-5500 cal，到了两千年后的3600-3500 BCE，当时新石器时代的社区稳定地占据了大部分可用土地。从比利牛斯山脉山区到地中海沿岸地区。在这种情况下，伊比利亚半岛东北部是进行过大量使用磨损分析的地区之一，尤其是在关注方面新石器时代，这主要是由于发掘负责人和西班牙使用服装专家表现出的浓厚兴趣；他们参与和合作以扩大孔蒂的数量xts进行了研究，使伊比利亚半岛的NE成为“功能研究”数量最多的欧洲地区之一。结果，今天我们可以可靠地了解第一批耕作小组使用的石器工具的类型，使用方法以及它们满足的需求。今天，大多数使用方法广泛共享用于这种类型的分析的方法穿专家。立体显微镜与反射光显微镜一起用于分析考古样本。然后，将观察到的使用磨损痕迹与实验工具的痕迹进行比较。这项研究主要利用了巴塞罗那CSIC的米拉·丰塔纳尔研究所的“ Traceoteque”中保存的工具。本文介绍了针对不同类型的分析地点和相对石器组合所获得的结果。通过这种方式，可以比较来自不同环境的工具：露天场所，洞穴和岩石避难所，露天场所，埋葬场所和采矿场所。如此多样的上下文允许探索重复性的存在以及从一个站点到另一个站点的石器工具的功能差异。所获得的结果还提供了与在不同地点，洞穴，避难所和露天环境中进行的经济过程有关的某些方面的信息。可以获得有关所执行任务的类型及其对每个站点的相对重要性，它们与地理和环境环境以及那里可用自然资源的关系的新数据。此外，对从墓葬中回收的工具（主要是个人遗体）进行分析，可提供有关被掩埋的个体与工作工具之间关系的信息，尤其是探索性别与年龄模式之间的关系以及作为商品存放的工具的类型。磨损分析允许探索各种问题；从与石器资源的生产和管理有关的技术方面到与自给活动及其实施者有关的社会方面。”

HOW TO USE GRAPHS TO DIAGNOSE AND DEAL WITH BAD EXPERIMENTAL DATA

摘要

著录项

相似文献

相关主题

期刊订阅