Talk:Restricted randomization

Untitled
Here's the current opening paragraph of this article:
 * Many processes have more than one source of variation in them. In order to reduce variation in processes, these multiple sources must be understood, and that often leads to the concept of nested or hierarchical data structures. For example, in the semiconductor industry, a batch process may operate on several wafers at a time (wafers are said to be nested within batch). Understanding the input variables that control variation among those wafers, as well as understanding the variation across each wafer in a run, is an important part of the strategy for minimizing the total variation in the system.
 * Many processes have more than one source of variation in them. In order to reduce variation in processes, these multiple sources must be understood, and that often leads to the concept of nested or hierarchical data structures. For example, in the semiconductor industry, a batch process may operate on several wafers at a time (wafers are said to be nested within batch). Understanding the input variables that control variation among those wafers, as well as understanding the variation across each wafer in a run, is an important part of the strategy for minimizing the total variation in the system.

That is a horrible introduction!

The fact is, I found this page because split plot redirects to it. A split plot design is indeed a form of restricted randomization. But it doesn't fit into what this introductory paragraph is about. "Process" gets links to (of all things!!!) process (engineering). The paragraph makes it sound as if the topic is about desirable reduction in variability! Split plot designs and other experimental designs are not about how to reduce variability; they're about how to design and interpret experiments when variability is present among experimental units.

The first sentence doesn't give the lay reader any impression of what the topic of the article is. That needs to get fixed. The second sentence makes it appear that it might be about reducing variation. That's wrong if "split plot" and the like are to redirect here. Michael Hardy (talk) 21:21, 20 June 2009 (UTC)


 * I have added the intro-rewrite tag because I have the same problems as detailed above. Melcombe (talk) 15:06, 21 September 2009 (UTC)

Page appears to be copy & pasted
In case somebody does come along to try to fix this monster, be aware that the bulk of the article appears to be copy & pasted from NIST. 12.250.110.6 (talk) 22:33, 30 April 2013 (UTC)

Section 'Example of Nested Data' requires expertise in the domain of application to be understood
I'm lost by the opening sentence of this example: "Consider a batch process that uses 7 monitor wafers in each run. The plan further calls for measuring a response variable on each wafer at each of 9 sites. The organization of the sampling plan has a hierarchical or nested structure: the batch run is the topmost level, the second level is an individual wafer, and the third level is the site on the wafer." What's a wafer? Are we talking about silicon in electronic component manufacturing, or about a biological substrate? And what is a monitor wafer in particular? The example needs to be re-written using an application, and without jargon, so that it can be understood by a broad audience. 203.110.235.8 (talk) 01:45, 5 June 2020 (UTC)