蚀刻 发表于 2025-3-25 04:54:06
978-3-7908-1111-7Springer-Verlag Berlin Heidelberg 1998Fecal-Impaction 发表于 2025-3-25 08:10:35
MODA 5 - Advances in Model-Oriented Data Analysis and Experimental Design978-3-642-58988-1Series ISSN 1431-1968 Series E-ISSN 2628-8966AMEND 发表于 2025-3-25 15:11:04
http://reply.papertrans.cn/63/6202/620194/620194_23.png令人作呕 发表于 2025-3-25 17:30:04
Interval Analysis for Guaranteed Nonlinear Parameter EstimationEstimating the parameters of nonlinear models from experimental data often involves optimizing nonconvex cost functions. This introductory paper illustrates how interval analysis can be used to perform this task in a guaranteed way, in contrast with the usual local iterative methods.Accommodation 发表于 2025-3-25 22:42:13
A Numerical Study of Singularly Perturbed Markovian SystemsThis work is concerned with simulation and Monte Carlo study of singularly perturbed Markov chains. The convergence of the solution of the Kolmogorov forward equation for the corresponding probability distribution is demonstrated. The asymptotic normality is also presented.Bricklayer 发表于 2025-3-26 02:29:23
Optimum Chemical Balance Weighing Designs Under Equal Correlations of Errorsrrors in the usual linear model. A lower bound for the variance of each of the estimated weights resulting from this chemical balance weighing design is obtained and a necessary and sufficient condition for this lower bound to be attained is given.人工制品 发表于 2025-3-26 05:45:11
http://reply.papertrans.cn/63/6202/620194/620194_27.pngfoodstuff 发表于 2025-3-26 10:47:00
Comparison of Spectral and Hadamard Bounds for D-Optimalityequality which was introduced by Welch. In particular, we demonstrate that (i) in general, neither bound dominates the other . the spectral bound is superior in a general situation of highly replicated designs, and (iii) the spectral bound is superior when a very accurate bound is required in situations of singularity.后退 发表于 2025-3-26 12:53:08
http://reply.papertrans.cn/63/6202/620194/620194_29.pngPHONE 发表于 2025-3-26 17:08:07
Optimal Designs for Models with Ignored Heteroscedasticityue state of nature is heteroscedastic. A criterion that takes this type of misspecification into account is formulated and the corresponding equivalence condition for the D- and A- criteria are derived. Using the equivalence theorems, optimal designs are derived analytically for several types of efficiency functions.