Algorithm 33. Test for difference in trends in a two-factor experiment with repeated measurements
Algorithms for Optimal Design with Application to Multiple Polynomial Regression.
Algunas soluciones aproximadas para diseños split-plot con matrices de covarianza arbitrarias.
El presente trabajo revisa con cierto detalle diversos tipos de análisis para diseños split-plot que carecen del mismo número de unidades experimentales dentro de cada grupo y en los que se incumple el supuesto de esfericidad multimuestral. Específicamente, adoptando el enfoque multivariado de aproximar los grados de libertad desarrollado por Johansen (1980) y el procedimiento de aproximación general mejorada corregida basado en Huynh (1980) se muestra cómo obtener análisis robustos y poderosos...
Almost Saturated D -Optimal Main Effect Plans and Allied Results.
An empirical comparison of some experimental designs for the valuation of large variable annuity portfolios
Variable annuities contain complex guarantees, whose fair market value cannot be calculated in closed form. To value the guarantees, insurance companies rely heavily on Monte Carlo simulation, which is extremely computationally demanding for large portfolios of variable annuity policies. Metamodeling approaches have been proposed to address these computational issues. An important step of metamodeling approaches is the experimental design that selects a small number of representative variable annuity...
An Example of Universal Optimality in a Full-Rank Model.
An introduction to optimal designs.
Análisis de diseños factoriales sin replicación.
En este artículo se propone un método para identificar efectos significativos en diseños factoriales sin replicación, resolviendo el problema como un caso de determinación de observaciones atípicas (outliers) en muestras altamente contaminadas. Para ello se deriva un estimador robusto de escala basándose en simulaciones realizadas con ordenador. El método es extremadamente sencillo de aplicar y conduce a los mismos resultados que el proyectado por Box y Meyer (1986) que es de mayor complejidad.
Analyse de la variance et indicatrices de modalités
Analysis of PBIB Designs Using Association Matrices.
Another View on Optimal Design for Estimating the Point of Extremum in Quadratic Regression.
A-optimal biased spring balance weighing design
In this paper we study the problem of estimation of individual measurements of objects in a biased spring balance weighing design under assumption that the errors are uncorrelated and they have different variances. The lower bound for the variance of each of the estimated measurements for this design and the necessary and sufficient conditions for this lower bound to be attained are given. The incidence matrices of the balanced incomplete block designs are used for construction of the A-optimal...
Asymptotic criteria for designs in nonlinear regression with model errors
Asymptotic optimality of experimental designs in estimating a product of means.
Balanced ternary designs with block size three, any ... and any R.
Bestimmung kostenoptimaler Parameter für den kontinuierlichen Stichprobenplan von DODGE.
Bounds on the Efficiency of the Residual Design of Extended BIB Designs.
Certain new M-matrices and their properties with applications
The Mₙ-matrix was defined by Mohan [21] who has shown a method of constructing (1,-1)-matrices and studied some of their properties. The (1,-1)-matrices were constructed and studied by Cohn [6], Ehrlich [9], Ehrlich and Zeller [10], and Wang [34]. But in this paper, while giving some resemblances of this matrix with a Hadamard matrix, and by naming it as an M-matrix, we show how to construct partially balanced incomplete block designs and some regular graphs by it. Two types of these M-matrices...
Characterizing experimental designs by properties of the standard quadratic forms of observations
For any orthogonal multi-way classification, the sums of squares appearing in the analysis of variance may be expressed by the standard quadratic forms involving only squares of the marginal and total sums of observations. In this case the forms are independent and nonnegative definite. We characterize all two-way classifications preserving these properties for some and for all of the standard quadratic forms.
Combined Unbiased Estimators Based on Q-Reduced Model.