More Restrictive Designs

Helge Toutenburg
Additional contact information
Helge Toutenburg: University of Munich, Institute of Statistics

Chapter 5 in Experimental Design and Model Choice, 1995, pp 145-165 from Springer

Abstract: Abstract In statistical practice, the experimental units are often not completely homogeneous. Usually, a grouping according to a stratification factor can be observed (clinical population: stratified according to patient’s age, degree of disease, etc.). If we have such prior information then a gain in efficiency compared to the completely randomized experiment is possible by grouping into blocks. The experimental units are grouped together in homogeneous groups (blocks) and the treatments are assigned to the experimental units within each block by random. Hence the block effect (differences between the blocks) can now be separated from the experimental error. This leads to a higher precision. The strategy of building blocks should yield a variability within each block that is as small as possible and a variability between blocks that is as high as possible.

Keywords: Experimental Unit; Block Effect; Randomize Block Design; Friedman Test; Column Effect (search for similar items in EconPapers)
Date: 1995
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-642-52498-1_5

Ordering information: This item can be ordered from
http://www.springer.com/9783642524981

DOI: 10.1007/978-3-642-52498-1_5

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().