Results 271 to 280 of about 13,560,800 (313)

D‐optimal minimax fractional factorial designs

Canadian Journal of Statistics, 2013
AbstractThe D‐optimal minimax criterion is proposed to construct fractional factorial designs. The resulting designs are very efficient, and robust against misspecification of the effects in the linear model. The criterion was first proposed by Wilmut & Zhou (2011); their work is limited to two‐level factorial designs, however.
Lin, Dennis K. J., Zhou, Julie
openaire   +1 more source

Training data development with the D-optimality criterion

IEEE Transactions on Neural Networks, 1999
The importance of using optimum experimental design (OED) concepts when selecting data for training a neural network is highlighted in this paper. We demonstrate that an optimality criterion borrowed from another field; namely the D-optimality criterion used in OED, can be used to enhance the training value of a small training data set.
M. H. Choueiki, C. A. Mount-Campbell
openaire   +3 more sources

D-optimality of complete latin squares

Series Statistics, 1982
Row-complete (complete) latin squares are characterized as the D-optimum designs for a linear model with row- (row- and column-) residual effects of first order.
openaire   +1 more source

D-optimal weighing designs for six objects

Metrika, 2000
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Neubauer, Michael G., Watkins, William, Zeitlin, Joel   +2 more
openaire   +2 more sources

D-optimality of the dual of BIB designs

Statistics & Probability Letters, 1992
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
openaire   +1 more source

On \(d\)-optimality of the LR tests

Kybernetika, 1995
Summary: The lower asymptotic distributional bound of the level attained is attained in the case of the likelihood ratio statistics. The regularity conditions on which the proofs are based are verified for the non-singular normal, the multinomial and the Poisson distribution.
openaire   +2 more sources

Soft selection in D-optimal designs

1994
A new algorithm generating the D-optimal experimental designs, based on an evolutionary search with soft selection, is presented. An efficiency of the numerical algorithm is compared with classical exchange algorithms. Preliminary results are promising and encourage more detailed investigations.
openaire   +2 more sources

D-optimal designs for weighted polynomial regression

Journal of Statistical Planning and Inference, 1997
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Chang, Fu-Chuen, Lin, Ge-Chen
openaire   +2 more sources

D-optimal designs for correlated random vectors

Journal of Statistical Planning and Inference, 2008
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Masaro, Joe, Wong, Chi Song
openaire   +2 more sources

D-optimal design for Becker's minimum polynomial

Statistics & Probability Letters, 2000
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
openaire   +1 more source