|
所在平台: Coursera |
课程主页: https://www.coursera.org/learn/measurement-systems-analysis
课程评论：没有评论
课程名称：测量系统分析 课程概述： 在本课程中，您将学习如何分析测量系统的过程稳定性和能力，以及在进行任何统计分析之前，稳定的测量过程为何至关重要。您将使用R软件分析连续测量系统，并统计性地表征准确性和精密度。课程将涵盖潜在的短期和长期统计控制及能力的测量系统分析。此外，您还将学习如何评估离散测量，并进行内部一致性、评估者之间的一致性以及与标准的一致性分析。最后，您将学习如何对测量系统进行过程改进的决策。 该专业可以作为科罗拉多大学博尔德分校的数据科学硕士（MS-DS）学位的一部分，申请并在Coursera平台上学习。MS-DS是一个跨学科的学位项目，聚集了博尔德大学应用数学、计算机科学、信息科学等多个学科的教师。凭借基于表现的招生方式和无需申请流程，MS-DS项目特别适合具有计算机科学、信息科学、数学和统计学等广泛背景的个人。了解更多关于MS-DS项目的信息，请访问 https://www.coursera.org/degrees/master-of-science-data-science-boulder。 课程大纲： 第1部分：相关性与关联 描述：在这一模块中，我们将学习识别、表征和分析两个变量之间的关系，包括连续变量的相关性、序数变量的相关性，以及名义变量与连续变量之间的关联。我们还将学习两名义变量之间关系的评估。 第2部分：固定和随机效应的一元方差分析（ANOVA） 描述：在这一模块中，我们将进行单因子的固定和随机效应方差分析，并解读结果。我们将检查组内和组间变异，并解读ANOVA源表，学习如何在考虑正态性和方差相等/不相等的情况下进行固定效应的均值和离散性方差分析，并进行结果的可视化。 第3部分：连续数据的测量系统分析简介，潜在研究 描述：在这一模块中，我们将了解测量系统分析中的术语和概念，分析测量误差以确定测量系统的潜在能力。我们将探讨测量系统分析的指南、测量误差和能力的公式，并通过方差分析计算变异来源。 第4部分：连续数据的短期和长期研究 描述：在这一模块中，我们将分析测量误差以确定测量系统的短期和长期能力。我们将在前一模块的基础上评估正态性、部分大小/幅度和测量误差的独立性以及测量误差的稳定性，并进行方差分析。 第5部分：离散数据的测量系统分析 描述：在这一模块中，我们将分析离散测量系统，评估一致性、有效性和内部一致性。我们将学习使用Kappa统计量测量一致性，评估评估者之间的一致性，以及与标准的一致性分析。
Part: 1
Title:Correlation and Association
Description:In this module, we will learn to identify, characterize and analyze relationships between two variables. We will first learn about correlation between two continuous variables and tests for significance. Next, we will learn about correlation for ordinal variables, and association for one nominal and one continuous variable. Finally, we will learn to assess relationship for two nominal variables.
Part: 2
Title:The One Way Analysis of Variance (ANOVA) for Fixed and Random Effects
Description:In this module, we will perform an Analysis of Variance for Fixed and Random Effects for a single factor and interpret results. We will first examine within versus between-group variation, and interpret the ANOVA source table. We will learn how to perform the ANOVA with Fixed Effects for means and dispersion, considering normality and equal/unequal variance. We'll create data visualizations of results, calculate statistical importance and perform post hoc analysis. Finally, we'll perform the ANOVA with Random Effects.
Part: 3
Title:Introduction to Measurement Systems Analysis for Continuous Data, Potential Studies for Continuous Data
Description:In this module, we will understand the terms and concepts associated with measurement systems analysis and analyze measurement error to determine the potential capability of a measurement system. We will explore the guidelines for measurement systems analyses and the equations for measurement error and capability. We will then calculate the sources of variation from the ANOVA determine the largest sources of variation, and determine capability in comparison to both process variation and specification tolerance. Finally, we'll create data visualizations, and interpret the results of the analysis.
Part: 4
Title:Short Term and Long Term Studies for Continuous Data
Description:In this module, we will analyze measurement error to determine the short and long-term capability of a measurement system. We will build on what we have learned in the previous module, adding the evaluation of the underlying assumptions of normality, independence of part size/magnitude and measurement error, and stability of measurement error. We'll perform an ANOVA to determine sources of variation along with the determination of gauge discrimination. Finally, we'll create data visualizations, and interpret the results of the analysis.
Part: 5
Title:Measurement Systems Analysis for Discrete Data
Description:In this module, we will analyze a discrete measurement system to determine agreement, consistency, and validity. We will first familiarize ourselves with the terms, definitions, and procedures associated with Discrete Measurement Systems Analysis. Next, we will explore the measurement of agreement using the Kappa statistic and the measure of disagreement using the test of symmetry. We will then learn to perform analyses for concordance with two appraisers and two categories, two appraisers more than two categories, and more than two appraisers. We will analyze appraisers for internal consistency. Finally, we'll assess validity (concordance with a standard).
In this course, you will learn to analyze measurement systems for process stability and capability and why having a stable measurement process is imperative prior to performing any statistical analysis. You will analyze continuous measurement systems and statistically characterize both accuracy and precision using R software. You will perform measurement systems analysis for potential, short-term and long-term statistical control and capability. Additionally, you will learn how to assess a discrete measurement and perform analyses for internal consistency, concordance between assessors, and concordance with a standard. Finally, you will learn how to make decisions on measurement systems process improvement. This specialization can be taken for academic credit as part of CU Boulder’s Master of Science in Data Science (MS-DS) degree offered on the Coursera platform. The MS-DS is an interdisciplinary degree that brings together faculty from CU Boulder’s departments of Applied Mathematics, Computer Science, Information Science, and others. With performance-based admissions and no application process, the MS-DS is ideal for individuals with a broad range of undergraduate education and/or professional experience in computer science, information science, mathematics, and statistics. Learn more about the MS-DS program at https://www.coursera.org/degrees/master-of-science-data-science-boulder.
