Statistics Toolbox

bbdesign

Generate Box-Behnken design

Syntax

• D = bbdesign(nfactors) 
  D = bbdesign(nfactors,'pname1',pvalue1,'pname2',pvalue2,...)
  [D,blk] = bbdesign(...)
  

Description

D = bbdesign(nfactors) generates a Box-Behnken design for nfactors factors. The output matrix D is n-by-nfactors, where n is the number of points in the design. Each row lists the settings for all factors, scaled between -1 and 1.

[D,blk] = bbdesign(nfactors) requests a blocked design. The output vector blk is a vector of block numbers. Blocks are groups of runs that are to be measured under similar conditions (for example, on the same day). Blocked designs minimize the effect of between-block differences on the parameter estimates.

[...] = bbdesign(nfactors,'pname1',pvalue1,'pname2',pvalue2,...) allows you to specify additional parameters and their values. Valid parameters are:

'center'	Number of center points to include.
'blocksize'	Maximum number of points allowed in a block.

Remarks

Box and Behnken proposed designs when the number of factors was equal to 3-7, 9-12, or 16. This function produces those designs. For other values of nfactors, this function produces designs that are constructed in a similar way, even though they were not tabulated by Box and Behnken, and they may be too large to be practical.

See Also

ccdesign, cordexch, rowexch

barttest

betacdf