dCE2 = daugment(dCE,mruns)
[dCE2,X] = daugment(dCE,mruns)
[dCE2,X] = daugment(dCE,mruns,
[dCE2,X] = daugment(...,
dCE2 = daugment(dCE,mruns) uses
a coordinate-exchange algorithm to D-optimally
mruns runs to an existing experimental design
a linear additive model.
[dCE2,X] = daugment(dCE,mruns) also
returns the design matrix
X associated with the
[dCE2,X] = daugment(dCE,mruns, uses
the linear regression model specified in
one of the following:
'linear'— Constant and linear terms. This is the default.
'interaction'— Constant, linear, and interaction terms
'quadratic'— Constant, linear, interaction, and squared terms
'purequadratic'— Constant, linear, and squared terms
The order of the columns of
X for a full
quadratic model with n terms is:
The constant term
The linear terms in order 1, 2, ..., n
The interaction terms in order (1, 2), (1, 3), ..., (1, n), (2, 3), ..., (n – 1, n)
The squared terms in order 1, 2, ..., n
Other models use a subset of these terms, in the same order.
model can be a matrix
specifying polynomial terms of arbitrary order. In this case,
have one column for each factor and one row for each term in the model.
The entries in any row of
model are powers
for the factors in the columns. For example, if a model has factors
X3, then a row
[0 1 2] in
(X1.^0).*(X2.^1).*(X3.^2). A row of all
model specifies a constant term,
which can be omitted.
[dCE2,X] = daugment(..., specifies
additional parameter/value pairs for the design. Valid parameters
and their values are listed in the following table.
Lower and upper bounds for each factor, specified as
Indices of categorical predictors.
Handle to a function that excludes undesirable runs.
If the function is f, it must support the syntax b = f(S),
where S is a matrix of treatments with
Initial design as an
Vector of number of levels for each factor.
Maximum number of iterations. The default is
The value is a structure that contains options specifying
whether to compute multiple tries in parallel, and specifying how
to use random numbers when generating the starting points for the
tries. Create the options structure with
Number of times to try to generate a design from a new
starting point. The algorithm uses random points for each try, except
possibly the first. The default is
daugment function augments an existing
design using a coordinate-exchange algorithm; the
candexch function provides
the same functionality using a row-exchange algorithm.
The following eight-run design is adequate for estimating main effects in a four-factor model:
dCEmain = cordexch(4,8) dCEmain = 1 -1 -1 1 -1 -1 1 1 -1 1 -1 1 1 1 1 -1 1 1 1 1 -1 1 -1 -1 1 -1 -1 -1 -1 -1 1 -1
To estimate the six interaction terms in the model, augment the design with eight additional runs:
dCEinteraction = daugment(dCEmain,8,'interaction') dCEinteraction = 1 -1 -1 1 -1 -1 1 1 -1 1 -1 1 1 1 1 -1 1 1 1 1 -1 1 -1 -1 1 -1 -1 -1 -1 -1 1 -1 -1 1 1 1 -1 -1 -1 -1 1 -1 1 -1 1 1 -1 1 -1 1 1 -1 1 1 -1 -1 1 -1 1 1 1 1 1 -1
The augmented design is full factorial, with the original eight runs in the first eight rows.
Automatic Parallel Support
Accelerate code by automatically running computation in parallel using Parallel Computing Toolbox™.
To run in parallel, specify the
'Options' name-value argument in the call
to this function and set the
'UseParallel' field of the options
For more information about parallel computing, see Run MATLAB Functions with Automatic Parallel Support (Parallel Computing Toolbox).