Low Risk Fits to Discrete Incomplete Multi-way Layouts
نویسنده
چکیده
The discrete multi-way layout is a widespread data-type associated with regression, experimental designs, gene or protein chips, digital images or videos, and more. A discrete multi-way layout has a finite number of factor level combinations. The layout may be unbalanced or incomplete or both. We consider candidate fits to an incomplete layout that are least squares fits to certain submodels induced by tensor product space ANOVA models for a complete layout. The candidate estimator with smallest estimated risk is selected. Multiparametric asymptotics under a general (saturated) Gaussian model show that the selected estimator achieves smallest asymptotic risk over the candidate class through bias-variance trade-off.
منابع مشابه
Tensor Product Space ANOVA Fits to Incomplete Unbalanced Discrete Multi-way Layouts
The discrete multi-way layout is a widespread data-type associated with experimental designs, gene or protein chips, digital images or videos, and more. A discrete multi-way layout has a finite number of factor level combinations. The layout may be unbalanced or incomplete or both. We consider candidate fits to an incomplete layout that are least squares fits to certain submodels induced by ten...
متن کاملMultiple Penalty Regression: Fitting and Extrapolating a Discrete Incomplete Multi-way Layout
The discrete multi-way layout is an abstract data-type associated with regression, experimental designs, digital images or videos, spatial statistics, gene or protein chips, and more. The factors influencing response can be nominal or ordinal. The observed factor level combinations are finitely discrete and often incomplete or irregularly spaced. This paper develops low risk biased estimators o...
متن کاملAdaptively Denoising Discrete Two-way Layouts
The two-way layout with ordinal or nominal factors is a fundamental data-type that is widespread in the sciences, engineering, and informatics. The unrestricted least squares estimator for the means of a two-way layout is usually inadmissible under quadratic loss and the model of homoscedastic independent Gaussian errors. In statistical practice, this least squares estimator may be modified by ...
متن کاملA New Multi-objective Model for Multi-mode Project Planning with Risk
The purpose of this problem is to choose a set of project activities for crashing, in a way that the expected project time, cost and risk are minimized and the expected quality is maximized. In this problem, each project activity can be performed with a specific executive mode. Each executive mode is characterized with four measures, namely the expected time, cost, quality and risk. In this pap...
متن کاملREACT Fits to Linear Models and Scatterplots
REACT estimators for the mean of a linear model involve three steps: transforming the model to a canonical form that provides an economical representation of the unknown mean vector, estimating the risks of a class of candidate linear shrinkage estimators, and adaptively selecting the candidate estimator that minimizes estimated risk. When the mean vector is smooth, the desired canonical form o...
متن کامل