What is it about?
This paper is the second of a short series of articles aimed towards describing some of the various statistical methods and approaches that have been used in surface finishing. The methods fall broadly into two areas: analysis and design-of-experiments. In the first paper, the subject was briefly introduced followed by a discussion of parametric statistics hypothesis testing. This second paper logically continues with descriptions of the various non-parametric tests and situations where these could be applied. Examples are provided from within the context of surface finishing applications, although the application of the described tests can be more universally applied.
Featured Image
Photo by rawpixel on Unsplash
Why is it important?
The understanding and use of statistics is important in all research methods. This paper is the second in a series, describing non-parametric statistical methods. The paper will be a good reference source for anyone needing a good grasp of when and how to apply non-parametric statistical methods. A light-touch mathematical approach is adopted which gives some detail about what's happening within the SPSS 'black box.
Perspectives
Read the Original
This page is a summary of: Statistical approaches in surface finishing. Part 2. non-parametric methods for data analysis, Transactions of the IMF, December 2018, Taylor & Francis,
DOI: 10.1080/00202967.2019.1555367.
You can read the full text:
Resources
Part 1 (parametric stats) free post-print version download
A free download postprint version of the stats paper.
Part 2 (non-parametric stats) free post-print version download
A free download postprint version of the stats paper.
Stats Part 1 URL
Web link to Part 1 Stats
SPSS Screenshot: Mann-Whitney U test
Steps required to perform a Mann-Whitney U test in SPSS
SPSS Screenshot: Wilcoxon signed rank test
SPSS Screenshot: Wilcoxon signed rank test
SPSS Screenshot: Kruskall-Wallis test
SPSS Screenshot: Kruskall-Wallis test
Contributors
The following have contributed to this page