Advertisement

More Restrictive Designs

  • Helge Toutenburg
  • Shalabh
Chapter
Part of the Springer Texts in Statistics book series (STS)

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 Randomize Block Design Friedman Test Training Method Simple Comparison 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  1. 1.Institut für StatistikLudwig-Maximilians-UniversitätMünchenGermany
  2. 2.Department of Mathematics & StatisticsIndian Institute of TechnologyKanpurIndia

Personalised recommendations