【校稿】第三十五篇 Tools and techniques to help process engineers do their jobs
本帖最后由 小编D 于 2012-1-6 10:53 编辑
你好，我是小编H。请对以下文章有翻译兴趣的组员留下你的预计完成时间，并发短信息联系小编H，以便小编登记翻译者信息以及文章最终完成时的奖惩工作。感谢支持翻译组！本文由jmc_ld翻译 工具和技术帮助过程工程师工作
by Robert L. Mason and John C. Young作者：罗伯特 L. 马森 & 约翰 C.杨
Many engineers working in processing industries often are overwhelmed bythe amount of data available to them. Until recently, most industries collectedonly a small amount of information on their processes. Process engineers hadfew observations on a small number of critical variables that helped makedecisions on how the process was to be operated. 许多工作在过程企业的工程师，经常全面收集对他们来说有用的大量数据。直到最近，许多企业只在他们的过程收集少量的信息。过程工程师只是在少量的关键变差进行取样，这样就能帮助他们确认如何介入过程。
That situation has changed. With the development of electronicdata-gathering systems, such as distributed control systems, process engineersnow have many observations available on a multitude of variables. They also canstore these observations electronically for study and review at any time.现在这个状况发生了改变。随着电子化数据收集系统的发展，例如分布式的控制系统，过程工程师可以对大量变量进行检测，并且可以通过电子化的存贮方式保留数据，并随时进行研究和回顾。
This task of gathering and maintaining observations has added an extradimension to a process engineer’s job. It has created a new role—statisticalengineer—that entails being able to transform the data observations into usefulprocess information. 检测数据的收集和保存成了过程工程师额外的工作。这样创造了一个新的角色-统计工程师-将检测数据转化为有用的过程信息的人。
Laying the foundation基础的需求
To do this, process engineers need a certain degree of proficiency inusing the appropriate statistical tools for analyzing many types of dataproblems. These problems can range from selecting random data samples todesigning statistical experiments. 要做这项工作，过程工程师需要在分析不同的数据问题时选择合适的统计工具的能力。这些数据问题包括为设计统计试验来选择随机性的数据样本的能力。
Process engineers also might need to know how to construct and applyvarious prediction (regression) equations. These analyses usually include theapplication of statistical process control procedures, covering univariate andmultivariate samples. In addition, there is a need in all areas of applicationto be able to test a statistical hypothesis. 过程工程师也可能需要知道创建和运用各种的预报（回归）方程式。这些分析通常包括统计过程控制的运用，包括单变量及多变量因子。另外，在各个运用区域具有测试统计性假设的能力。
In short, the increase in process data has led process engineers to seekmore training in statistics.一句话，过程数据的增加要求过程工程师在统计学上需要更多的培训。
This result immediately generates questions: "What type ofstatistical background is necessary to produce statistical engineers?" and"Where can such training be obtained?" It is doubtful this level oftraining is offered in an undergraduate engineering degree program at a localuniversity. Most university engineering degree curriculums are already filledwith required engineering courses and include limited time for external courseelectives, such as in statistics. 这个结论立即提出以下问题：“统计工程师需要怎样的统计学背景是必须的”和“哪里能够这的这样的培训”。在本土大学的工程师学位教程中是不提供这种层次的训练。大多数大学工程师学位教程已经被需要的工程课程占据，并且同时包括限时的选修课程，比如统计学。
Often, the educational requirements for this new role can be met byobtaining a master’s degree in applied statistics or attending statistics-orientedseminars and quality programs, such as those involving Six Sigma. 通常，对于这个新角色的培训需求需要在统计运用或者参加统计指引研究会和质量标准制定协会中获得大师级别的人，比如那些研究6西格玛的人。
Statistical courses recommended for someone serving as a statisticalengineer can vary. A first course (for example, applied statistics I) usuallycontains data presentation (frequency tables, histograms and box plots),descriptive statistics (mean, median, mode, range, variance, standarddeviation, quartile and quantile), basic normal probability theory and statisticalhypothesis testing. Several one-sample testing procedures—such as the binomialtest, normal test and the t-test—are detailed, along with confidence intervals.The appropriate tests of hypotheses for (one-sample) variance problems are alsoincluded. 为统计工程师的推荐统计学课程是可变的。第一节课程（举例，统计学运用1）通常包括数据的描述（频数分布表、直方图和箱型图），统计描述（意思，中值，样式，范围，变量，基础变差，四分位数和分位数），基础正态分布概率理论和统计性假设测试。集中单一因子测试过程-比如二次分布测试，正态分布测试和T测试-具体详细的，同时还有置信区间的解释。对（单一因子）变量问题的统计假设的测试方式选择也是培训内容。
A continuation of this course (for example, applied statistics II) willexpand the coverage to two-sample tests of hypotheses for the mean (forexample, two sample t-test and paired t-test) and the two-sample variance test(for example, the F-test The chi-square goodness of fit test through theone-way analysis of variance (ANOVA) procedure will also be covered. 接下来的课程（比如，统计运用2）会延展到双因子的假设性验证（比如，双因子T测试和成对T测试）和双因子方差检验（比如，F测试）。在匹配性测试中，通过单因子变差分析（ANOVA）所做的卡方测试的好处，课程也同样涉及。
An important topic covered in this second course is the correlationbetween two variables. Not only is the technical definition of correlationpresented, but graphical techniques are also introduced to recognize whencorrelation exists between two variables. 在这个第二阶段的课程中，一个重要的课题是两变量间的关联性。当两变量间存在关联时，介绍认识的不仅仅是技术层面上对关联的定义，还包括图示化技术。
Figure 1 shows a scatterplot of the shoe size versus height of 85 male collegestudents. In this plot, the height variable increases as the shoe sizeincreases. In general, this second set of applied statistics courses emphasizesthe appropriate application of these procedures.图表1为85位男性大学生鞋长与身高的散点图。从图中，我们可以知道随着鞋长的增加，身高也在变化增加。通常的，第二阶段统计学运用课程强调针对过程的合适的统计工具运用。
We cannot overemphasize the importance of these two foundational courses,which lay the groundwork for the development of other statistical procedures.For example, it is easy to develop Shewhart charting procedures (univariatestatistical process control) by establishing confidence intervals on thepopulation mean. Also, good coverage of the testing of hypotheses of equalmeans for the two-sample problem provides a natural lead-in to ANOVAprocedures. 我们不能过分强调这两个基础课程的重要性，他们也可以通过其他的统计学课程获得。比如，通过总体平均值建立置信区间来建立的休哈特图形教程（单变量统计过程控制）很容易学习掌握。同样，对双因子假设性测试问题，一个等同的手段是自然导入变差分析（ANOVA）课程。
Knowing ANOVA了解变差分析
ANOVA procedures constitute a second important area of statisticalconcentration for a statistics engineer. This topic is important not only inlearning how to compute different ANOVA procedures (for example, one-way andtwo-way), but also to understand experimental design concepts, such ascompletely randomized design, randomized block design and factorial design. 对一个统计工程师来说，ANOVA过程是统计学精华中的第二个重要部分。这个课题的重要性不仅仅是学习如何计算不同的ANOVA过程（比如，单因子和双因子），同时也要理解实验性设计的概念。例如完全随机设计，随机区组设计及因子设计。
For example, in a block design, similar experimental units are groupedtogether to form a homogenous group called a statistical block. Units betweenblocks, however, are different. By combining several blocks in an experiment,you can improve the efficiency of the design because a source of variation—theblocks—has been accounted for in the experiment. 举个例子，在区组设计中，实验类似的单元汇总到一起形成一个同质组，被称为统计性区组。不同区组的单元无论如何都是不同的。通过在一个实验中加入不同的区组，你可以提高设计的效率，因为一系列的变化通过区组在实验中已经被区分了。
Consider the nine different circles in Figure 2. Using a block design, youarrange the circles into three blocks, with three similar circles within eachblock, shown in Figure 3. 区分图表2中的9个不同的循环。使用区组设计，我们可以将这些循环归类在3个区组中，每个组曲有3个相似的循环，见图表3
http://www.asq.org/img/qp/101183-figure3.gif
Notice the variation within the three blocks is minimal. The variationbetween the blocks, which is due to the heterogeneity of the blocks, can be includedas a source of variation in the ANOVA. 观察这3个区组内的变化是极其微小的。区组间的变化，由于区组的不同，在ANOVA中属于一系列的变差。
After learning the concept of blocking, the process engineer usuallyunderstands how to control the effect of an extraneous variable on the totalvariation of an experiment. 通过学习区组的概念后，过程工程师通常可以了解如何控制一个外来变化在一个实验中对总变差的影响。
For example, by holding the temperature constant for each block, thevariation of a temperature component can be removed from the total processvariation. The process engineer quickly realizes this concept can be extendedand that more than one variable can be blocked. This may be the first time theengineer has been exposed to the concept of changing the value of more than onevariable in an experiment. 举个例子，通过对每个区组的温度控制，温度的变差就可以从总变差中移除了。过程工程师能够很快的掌握这个概念并了解不止一个变量可以被区分。这也许是工程师第一次在一个试验中通过改变不止一个变量而获得的概念。
Multivariate techniques a must多变量技术必须具备
A third area of study that is as important as the first two is appliedmultivariate techniques. 和前两部分课程同样重要的第三部分的学习是多变量技术的运用。
The first multivariate technique is multiple regression analysis. Thisprocedure is necessary if you are going to examine many variables that areinterrelated and move together as a group. 第一个多变量技术是多重回归分析。如果你想验证关联在一起的多重变量，这个是必须的过程。
Examples include the many variables associated with certain chemicalprocesses and the numerous variables involved with the generation ofelectricity. In both cases, the variables form a multivariate group—that is, aninterrelated group of variables that move together and are not independent ofone another.1例子包含有关某种化学反应或者电学反应的大量变量。在这两过程中，变量来自多变量的族群-这个多变量族群指一组相关联的变量组合在一起而且相互不独立存在。
There are numerous applications of multiple regression techniques in anindustrial process. Through these applications, the engineer learns how toconstruct the best prediction equation for the variable of interest in terms ofthe observations taken on the other related variables. 在工业生产过程中，多重回归分析技术得到大量的运用。通过这些运用，工程师学会如何为感兴趣的变量构建最好的预报方程，依据另外一些相关联的变量观测。
For example, you might be interested in predicting the amount of fuel usedto produce a certain amount of electricity. Also, through residual analysis,2you learn how to examine the variable of interest with the effect of anothervariable removed. This technique also can be extended to remove a timedependency (autocorrelation) within an individual variable. This can be anextremely valuable tool when analyzing autocorrelated data. 举例说，你可能想通过多少燃料预测可以生产多少电。同样，通过残差分析，你知道如何通过另一个变量的移除来检验对感兴趣变量的影响。这个技术同样可以运用在不随时间变化的单一变量上（自相关过程）。当分析自相关过程数据这个是非常有用的工具。
Another important use of regression analysis is the study of totalvariation of a system and how an individual variable contributes to the totalvariation. 回归分析的另外一个重要运用是一个系统的全变量研究和单一变量是如何影响总变量的。
An additional benefit gained from studying multiple regression analysis isthat it encourages the student to think in terms of many variables—not justone. It also reinforces the concept that more than one variable can be changedat a time. This opens the door to examine applying other useful multivariatetechniques. 通过多重回归分析的研究，我们能够获得另外一个好处，它鼓励学生就多变量进行思考，而不是只是单一变量。同时，它强化了这样一个概念，不止一种变量在随着时间变化。这些为其他别的有用的多变量技术检验运用提供了基础。
One of these is principal component analysis,3 and another isdiscriminant analysis. Discriminant analysis is a multivariate technique thatallows you to determine group membership for a particular observation. Based ona credit report, for example, it can be determined whether an individual is agood credit risk. This procedure has wide application in the process industryin making a decision as to the quality of the product. 这些技术中还包括主成分分析，还有辨别分析。辨别分析是一项多变量技术，它允许你决定对群组成员进行个特别的观测。依据一个信用报告，比如，它能确认一个个体是否有好的信用风险。这个工具在工业上被广泛运用于对产品质量做决定的时候。
Add SPC skills增加统计过程控制技能
If a fourth statistical competency is to be added for the statisticalengineer, it should be in the area of statistical process control (SPC Manycompanies are involved with some form of quality control either at theunivariate or multivariate level.4 Applying SPC techniques can solvemany day-to-day problems, reduce cost and produce a better quality product.对于一个统计工程师，第四个需要的技能，应该是在统计过程控制的范畴了。许多公司，不管在单变量还是多变量层面上，都有一些质量控制的表格运用。SPC技术可以解决许多日常性的问题，降低费用和提高产品质量水平。
A good understanding of basic applied statistical procedures, ANOVA andexperimental design techniques, multiple regression analysis and other appliedmultivariate techniques, and SPC will provide the best statistical backgroundfor a statistical engineer. 对基础的统计学运用良好的理解，变差分析和实验设计技术，多重回归分析和其他多变量技术运用，和SPC，是一个统计工程师最好的统计学技术背景。
You might think we’re trying to make statisticians out of engineers. Thisis not the case. Statistical engineers are engineers first, and they continueto be primarily concerned with the job of running processing units. Statisticscan provide an additional set of tools to help engineers accomplish thisgoal. 你可能在想我们努力成为统计学家，而不是工程师。事实并非如此。统计工程师首先是工程师，他们不停的对工作中的运行单元进行关心。统计技术能够提供一些额外的工具帮助他们实现目标。
你好，我是小编H。请对以下文章有翻译兴趣的组员留下你的预计完成时间，并发短信息联系小编H，以便小编登记翻译者信息以及文章最终完成时的奖惩工作。感谢支持翻译组！本文由jmc_ld翻译 工具和技术帮助过程工程师工作
by Robert L. Mason and John C. Young作者：罗伯特 L. 马森 & 约翰 C.杨
Many engineers working in processing industries often are overwhelmed bythe amount of data available to them. Until recently, most industries collectedonly a small amount of information on their processes. Process engineers hadfew observations on a small number of critical variables that helped makedecisions on how the process was to be operated. 许多工作在过程企业的工程师，经常全面收集对他们来说有用的大量数据。直到最近，许多企业只在他们的过程收集少量的信息。过程工程师只是在少量的关键变差进行取样，这样就能帮助他们确认如何介入过程。
That situation has changed. With the development of electronicdata-gathering systems, such as distributed control systems, process engineersnow have many observations available on a multitude of variables. They also canstore these observations electronically for study and review at any time.现在这个状况发生了改变。随着电子化数据收集系统的发展，例如分布式的控制系统，过程工程师可以对大量变量进行检测，并且可以通过电子化的存贮方式保留数据，并随时进行研究和回顾。
This task of gathering and maintaining observations has added an extradimension to a process engineer’s job. It has created a new role—statisticalengineer—that entails being able to transform the data observations into usefulprocess information. 检测数据的收集和保存成了过程工程师额外的工作。这样创造了一个新的角色-统计工程师-将检测数据转化为有用的过程信息的人。
Laying the foundation基础的需求
To do this, process engineers need a certain degree of proficiency inusing the appropriate statistical tools for analyzing many types of dataproblems. These problems can range from selecting random data samples todesigning statistical experiments. 要做这项工作，过程工程师需要在分析不同的数据问题时选择合适的统计工具的能力。这些数据问题包括为设计统计试验来选择随机性的数据样本的能力。
Process engineers also might need to know how to construct and applyvarious prediction (regression) equations. These analyses usually include theapplication of statistical process control procedures, covering univariate andmultivariate samples. In addition, there is a need in all areas of applicationto be able to test a statistical hypothesis. 过程工程师也可能需要知道创建和运用各种的预报（回归）方程式。这些分析通常包括统计过程控制的运用，包括单变量及多变量因子。另外，在各个运用区域具有测试统计性假设的能力。
In short, the increase in process data has led process engineers to seekmore training in statistics.一句话，过程数据的增加要求过程工程师在统计学上需要更多的培训。
This result immediately generates questions: "What type ofstatistical background is necessary to produce statistical engineers?" and"Where can such training be obtained?" It is doubtful this level oftraining is offered in an undergraduate engineering degree program at a localuniversity. Most university engineering degree curriculums are already filledwith required engineering courses and include limited time for external courseelectives, such as in statistics. 这个结论立即提出以下问题：“统计工程师需要怎样的统计学背景是必须的”和“哪里能够这的这样的培训”。在本土大学的工程师学位教程中是不提供这种层次的训练。大多数大学工程师学位教程已经被需要的工程课程占据，并且同时包括限时的选修课程，比如统计学。
Often, the educational requirements for this new role can be met byobtaining a master’s degree in applied statistics or attending statistics-orientedseminars and quality programs, such as those involving Six Sigma. 通常，对于这个新角色的培训需求需要在统计运用或者参加统计指引研究会和质量标准制定协会中获得大师级别的人，比如那些研究6西格玛的人。
Statistical courses recommended for someone serving as a statisticalengineer can vary. A first course (for example, applied statistics I) usuallycontains data presentation (frequency tables, histograms and box plots),descriptive statistics (mean, median, mode, range, variance, standarddeviation, quartile and quantile), basic normal probability theory and statisticalhypothesis testing. Several one-sample testing procedures—such as the binomialtest, normal test and the t-test—are detailed, along with confidence intervals.The appropriate tests of hypotheses for (one-sample) variance problems are alsoincluded. 为统计工程师的推荐统计学课程是可变的。第一节课程（举例，统计学运用1）通常包括数据的描述（频数分布表、直方图和箱型图），统计描述（意思，中值，样式，范围，变量，基础变差，四分位数和分位数），基础正态分布概率理论和统计性假设测试。集中单一因子测试过程-比如二次分布测试，正态分布测试和T测试-具体详细的，同时还有置信区间的解释。对（单一因子）变量问题的统计假设的测试方式选择也是培训内容。
A continuation of this course (for example, applied statistics II) willexpand the coverage to two-sample tests of hypotheses for the mean (forexample, two sample t-test and paired t-test) and the two-sample variance test(for example, the F-test The chi-square goodness of fit test through theone-way analysis of variance (ANOVA) procedure will also be covered. 接下来的课程（比如，统计运用2）会延展到双因子的假设性验证（比如，双因子T测试和成对T测试）和双因子方差检验（比如，F测试）。在匹配性测试中，通过单因子变差分析（ANOVA）所做的卡方测试的好处，课程也同样涉及。
An important topic covered in this second course is the correlationbetween two variables. Not only is the technical definition of correlationpresented, but graphical techniques are also introduced to recognize whencorrelation exists between two variables. 在这个第二阶段的课程中，一个重要的课题是两变量间的关联性。当两变量间存在关联时，介绍认识的不仅仅是技术层面上对关联的定义，还包括图示化技术。
Figure 1 shows a scatterplot of the shoe size versus height of 85 male collegestudents. In this plot, the height variable increases as the shoe sizeincreases. In general, this second set of applied statistics courses emphasizesthe appropriate application of these procedures.图表1为85位男性大学生鞋长与身高的散点图。从图中，我们可以知道随着鞋长的增加，身高也在变化增加。通常的，第二阶段统计学运用课程强调针对过程的合适的统计工具运用。
We cannot overemphasize the importance of these two foundational courses,which lay the groundwork for the development of other statistical procedures.For example, it is easy to develop Shewhart charting procedures (univariatestatistical process control) by establishing confidence intervals on thepopulation mean. Also, good coverage of the testing of hypotheses of equalmeans for the two-sample problem provides a natural lead-in to ANOVAprocedures. 我们不能过分强调这两个基础课程的重要性，他们也可以通过其他的统计学课程获得。比如，通过总体平均值建立置信区间来建立的休哈特图形教程（单变量统计过程控制）很容易学习掌握。同样，对双因子假设性测试问题，一个等同的手段是自然导入变差分析（ANOVA）课程。
Knowing ANOVA了解变差分析
ANOVA procedures constitute a second important area of statisticalconcentration for a statistics engineer. This topic is important not only inlearning how to compute different ANOVA procedures (for example, one-way andtwo-way), but also to understand experimental design concepts, such ascompletely randomized design, randomized block design and factorial design. 对一个统计工程师来说，ANOVA过程是统计学精华中的第二个重要部分。这个课题的重要性不仅仅是学习如何计算不同的ANOVA过程（比如，单因子和双因子），同时也要理解实验性设计的概念。例如完全随机设计，随机区组设计及因子设计。
For example, in a block design, similar experimental units are groupedtogether to form a homogenous group called a statistical block. Units betweenblocks, however, are different. By combining several blocks in an experiment,you can improve the efficiency of the design because a source of variation—theblocks—has been accounted for in the experiment. 举个例子，在区组设计中，实验类似的单元汇总到一起形成一个同质组，被称为统计性区组。不同区组的单元无论如何都是不同的。通过在一个实验中加入不同的区组，你可以提高设计的效率，因为一系列的变化通过区组在实验中已经被区分了。
Consider the nine different circles in Figure 2. Using a block design, youarrange the circles into three blocks, with three similar circles within eachblock, shown in Figure 3. 区分图表2中的9个不同的循环。使用区组设计，我们可以将这些循环归类在3个区组中，每个组曲有3个相似的循环，见图表3
http://www.asq.org/img/qp/101183-figure3.gif
Notice the variation within the three blocks is minimal. The variationbetween the blocks, which is due to the heterogeneity of the blocks, can be includedas a source of variation in the ANOVA. 观察这3个区组内的变化是极其微小的。区组间的变化，由于区组的不同，在ANOVA中属于一系列的变差。
After learning the concept of blocking, the process engineer usuallyunderstands how to control the effect of an extraneous variable on the totalvariation of an experiment. 通过学习区组的概念后，过程工程师通常可以了解如何控制一个外来变化在一个实验中对总变差的影响。
For example, by holding the temperature constant for each block, thevariation of a temperature component can be removed from the total processvariation. The process engineer quickly realizes this concept can be extendedand that more than one variable can be blocked. This may be the first time theengineer has been exposed to the concept of changing the value of more than onevariable in an experiment. 举个例子，通过对每个区组的温度控制，温度的变差就可以从总变差中移除了。过程工程师能够很快的掌握这个概念并了解不止一个变量可以被区分。这也许是工程师第一次在一个试验中通过改变不止一个变量而获得的概念。
Multivariate techniques a must多变量技术必须具备
A third area of study that is as important as the first two is appliedmultivariate techniques. 和前两部分课程同样重要的第三部分的学习是多变量技术的运用。
The first multivariate technique is multiple regression analysis. Thisprocedure is necessary if you are going to examine many variables that areinterrelated and move together as a group. 第一个多变量技术是多重回归分析。如果你想验证关联在一起的多重变量，这个是必须的过程。
Examples include the many variables associated with certain chemicalprocesses and the numerous variables involved with the generation ofelectricity. In both cases, the variables form a multivariate group—that is, aninterrelated group of variables that move together and are not independent ofone another.1例子包含有关某种化学反应或者电学反应的大量变量。在这两过程中，变量来自多变量的族群-这个多变量族群指一组相关联的变量组合在一起而且相互不独立存在。
There are numerous applications of multiple regression techniques in anindustrial process. Through these applications, the engineer learns how toconstruct the best prediction equation for the variable of interest in terms ofthe observations taken on the other related variables. 在工业生产过程中，多重回归分析技术得到大量的运用。通过这些运用，工程师学会如何为感兴趣的变量构建最好的预报方程，依据另外一些相关联的变量观测。
For example, you might be interested in predicting the amount of fuel usedto produce a certain amount of electricity. Also, through residual analysis,2you learn how to examine the variable of interest with the effect of anothervariable removed. This technique also can be extended to remove a timedependency (autocorrelation) within an individual variable. This can be anextremely valuable tool when analyzing autocorrelated data. 举例说，你可能想通过多少燃料预测可以生产多少电。同样，通过残差分析，你知道如何通过另一个变量的移除来检验对感兴趣变量的影响。这个技术同样可以运用在不随时间变化的单一变量上（自相关过程）。当分析自相关过程数据这个是非常有用的工具。
Another important use of regression analysis is the study of totalvariation of a system and how an individual variable contributes to the totalvariation. 回归分析的另外一个重要运用是一个系统的全变量研究和单一变量是如何影响总变量的。
An additional benefit gained from studying multiple regression analysis isthat it encourages the student to think in terms of many variables—not justone. It also reinforces the concept that more than one variable can be changedat a time. This opens the door to examine applying other useful multivariatetechniques. 通过多重回归分析的研究，我们能够获得另外一个好处，它鼓励学生就多变量进行思考，而不是只是单一变量。同时，它强化了这样一个概念，不止一种变量在随着时间变化。这些为其他别的有用的多变量技术检验运用提供了基础。
One of these is principal component analysis,3 and another isdiscriminant analysis. Discriminant analysis is a multivariate technique thatallows you to determine group membership for a particular observation. Based ona credit report, for example, it can be determined whether an individual is agood credit risk. This procedure has wide application in the process industryin making a decision as to the quality of the product. 这些技术中还包括主成分分析，还有辨别分析。辨别分析是一项多变量技术，它允许你决定对群组成员进行个特别的观测。依据一个信用报告，比如，它能确认一个个体是否有好的信用风险。这个工具在工业上被广泛运用于对产品质量做决定的时候。
Add SPC skills增加统计过程控制技能
If a fourth statistical competency is to be added for the statisticalengineer, it should be in the area of statistical process control (SPC Manycompanies are involved with some form of quality control either at theunivariate or multivariate level.4 Applying SPC techniques can solvemany day-to-day problems, reduce cost and produce a better quality product.对于一个统计工程师，第四个需要的技能，应该是在统计过程控制的范畴了。许多公司，不管在单变量还是多变量层面上，都有一些质量控制的表格运用。SPC技术可以解决许多日常性的问题，降低费用和提高产品质量水平。
A good understanding of basic applied statistical procedures, ANOVA andexperimental design techniques, multiple regression analysis and other appliedmultivariate techniques, and SPC will provide the best statistical backgroundfor a statistical engineer. 对基础的统计学运用良好的理解，变差分析和实验设计技术，多重回归分析和其他多变量技术运用，和SPC，是一个统计工程师最好的统计学技术背景。
You might think we’re trying to make statisticians out of engineers. Thisis not the case. Statistical engineers are engineers first, and they continueto be primarily concerned with the job of running processing units. Statisticscan provide an additional set of tools to help engineers accomplish thisgoal. 你可能在想我们努力成为统计学家，而不是工程师。事实并非如此。统计工程师首先是工程师，他们不停的对工作中的运行单元进行关心。统计技术能够提供一些额外的工具帮助他们实现目标。
没有找到相关结果
已邀请:
RSS Feed
1 个回复
凌丹_sta (威望:46) (江西 南昌) 汽车制造相关 经理
赞同来自: