Optimal Designs for Best Linear Unbiased Prediction in Diallel Crosses

ABSTRACT

Recently, Ghosh and Das (2003 Ghosh , H. , Das , A. ( 2003 ). Optimal diallel cross designs for estimation of heritability . J. Statist. Plann. Inference 116 : 185 – 196 . [Google Scholar]) considered the estimation of variance components and the variances of these estimates. While comparing the yielding capacities of the cross (i, j), Kempthorne and Curnow (1961 Kempthorne , O. , Curnow , R. N. ( 1961 ). The partial diallel cross . Biometrics 17 : 229 – 250 .[Crossref], [Web of Science ®] , [Google Scholar]) proposed the estimation of the yielding capacity of any cross based on the least square estimators of the general combining ability effects and/or the mean yield of the cross (i, j). In this article, the problem of predicting the yielding capacity of the cross (i, j) from the sample of inbred lines has been considered. The properties of the best linear unbiased predictor for predicting the unobserved general combining ability effects together with general mean effect has been studied. We characterize A-optimal complete diallel cross designs and some efficient partial diallel cross designs under this setup.     

Forecasting the Distribution of Economic Variables in a Data-Rich Environment

This article investigates the relevance of considering a large number of macroeconomic indicators to forecast the complete distribution of a variable. The baseline time series model is a semiparametric specification based on the quantile autoregressive (QAR) model that assumes that the quantiles depend on the lagged values of the variable. We then augment the time series model with macroeconomic information from a large dataset by including principal components or a subset of variables selected by LASSO. We forecast the distribution of the h-month growth rate for four economic variables from 1975 to 2011 and evaluate the forecast accuracy relative to a stochastic volatility model using the quantile score. The results for the output and employment measures indicate that the multivariate models outperform the time series forecasts, in particular at long horizons and in tails of the distribution, while for the inflation variables the improved performance occurs mostly at the 6-month horizon. We also illustrate the practical relevance of predicting the distribution by considering forecasts at three dates during the last recession.     

A bayesian analysis of the intraclass correlations in the mixed linear model

This article is concerned with the study of intraclass correlations in the mixed linear model. A brief account of the shortcomings of the existing meth¬ods (frequentist. likelihood and Bayesian) is followed by alternative Bayesian parametrizations involving intraclass correlations and variance ratios. Our prior specifications accommodate a priori dependencies as well as situations which involve little or no prior information. We give examples of interval estimation and hypothesis testing using data from an animal breeding study.     

Continuity and Analysis of Sequences of Principal Components

Double arrays of n rows and p columns can be regarded as n drawings from some p-dimensional population. A sequence of such arrays is considered. Principal component analysis for each array forms sequences of sample principal components and eigenvalues. The continuity of these sequences, in the sense of convergence with probability one and convergence in probability, is investigated, that appears to be informative for pattern study and prediction of principal components. Various features of paths of sequences of population principal components are highlighted through an example.     

Reliability modeling of systems with two dependent degrading components based on gamma processes

Abstract

Many engineering systems have multiple components with more than one degradation measure which is dependent on each other due to their complex failure mechanisms, which results in some insurmountable difficulties for reliability work in engineering. To overcome these difficulties, the system reliability prediction approaches based on performance degradation theory develop rapidly in recent years, and show their superiority over the traditional approaches in many applications. This paper proposes reliability models of systems with two dependent degrading components. It is assumed that the degradation paths of the components are governed by gamma processes. For a parallel system, its failure probability function can be approximated by the bivariate Birnbaum–Saunders distribution. According to the relationship of parallel and series systems, it is easy to find that the failure probability function of a series system can be expressed by the bivariate Birnbaum–Saunders distribution and its marginal distributions. The model in such a situation is very complicated and analytically intractable, and becomes cumbersome from a computational viewpoint. For this reason, the Bayesian Markov chain Monte Carlo method is developed for this problem that allows the maximum likelihood estimates of the parameters to be determined in an efficient manner. After that, the confidence intervals of the failure probability of systems are given. For an illustration of the proposed model, a numerical example about railway track is presented.     

Least absolute relative error estimation for functional quadratic multiplicative model

ABSTRACT

As an alternative to the functional quadratic model due to Yao and Müller (2010 Yao, F., Müller, H.-G. (2010). Functional quadratic regression. Biometrika 97:49–64.[Crossref], [Web of Science ®] , [Google Scholar]), we consider a functional quadratic multiplicative model. This multiplicative model provides a useful alternative when the relative error is considered for analyzing data with positive responses. The existing work for functional models are mainly based on absolute errors. The commonly used least squares criterion is just such an example. In many practical applications, however, people concern on the size of relative error rather than that of error itself. Therefore, the estimation procedure based on least absolute relative errors, which is proposed by Chen et al. (2010 Chen, K., Guo, S., Lin, Y., Ying, Z. (2010). Least absolute relative error estimation. J. Am. Stat. Assoc. 105:1104–1112.[Taylor & Francis Online], [Web of Science ®] , [Google Scholar]) for the linear multiplicative model, is developed for functional quadratic multiplicative model. The asymptotic behaviors of the proposed estimators are established. Some simulation studies show that the estimation procedure has good prediction performance. Moreover, a real data set is analyzed for illustrating the proposed methods.     

The generalised inverse form of canonical correlation

The generalised inverse equations for the canonical correlation problem are derived using a minimum distance principle which-is shown to be equivalent to the usual maximum correlation formulation.     

The Robustness of the Three-Way Chart to Non Normality

In batch processing, the Three-Way control chart has been offered for controlling the mean of a process when the batch-to-batch variation is much greater than the within-batch variation. These two sources of variation are typically monitored along with usual batch sample means. Although the Three-Way chart was originally developed for normally distributed process data, its robustness to violations of the normality assumption is the central theme of this study. For data streams with heavy tails or displaying skewness, the in-control average run lengths (ARLs) for the Three-Way chart are seen to be significantly shorter than expected. On the other hand, out-of-control ARLs are much longer than the normal theory benchmarks for symmetric non-normal distributions. The Three-Way chart is not robust to moderate or strong skewness.     

Principal component analysis of canine hip dysplasia phenotypes and their statistical power for genome-wide association mapping

The aims of this study were to undertake principal component analysis (PCA) of hip dysplasia (HD) and to examine the power of the principal components (PCs) in genome-wide association studies. A cohort of 278 dogs for PCA and that of 369 dogs for genotyping were used. The distraction index (DI), the dorsolateral subluxation (DLS) score, the Norberg angle (NA), and the extended-hip radiographic (EHR) score were used for the PCA. One thousand single-nucleotide polymorphisms (SNPs) (of 23,500) were used to simulate genetic locus sharing between the HD phenotypes and 1000 SNPs were used to calculate the genetic mapping power of the PCs. The DI and the DLS score (first group) reflected hip laxity and the NA and the EHR score (second group) reflected the congruency between the femoral head and acetabulum. The average hip measurements of the two groups reflected in the first PC captured 55% of total radiographic variation. The first four PCs captured 90% of the total variation. The PCs had higher statistical mapping power to detect pleiotropic quantitative trait loci (QTL) than the raw phenotypes. The PCA demonstrated for the first time that HD can be reduced mathematically into simpler components essential for its genetic dissection. Genes that contribute jointly to all four radiographic hip phenotypes can be detected by mapping their first four PCs, while those contributing to individual phenotypes can be mapped by association with the individual raw phenotype.     

A Comparison of Estimation Methods on the Coverage Probability of Satterthwaite Confidence Intervals for Assay Precision with Unbalanced Data

Construction of closed-form confidence intervals on linear combinations of variance components were developed generically for balanced data and studied mainly for one-way and two-way random effects analysis of variance models. The Satterthwaite approach is easily generalized to unbalanced data and modified to increase its coverage probability. They are applied on measures of assay precision in combination with (restricted) maximum likelihood and Henderson III Type 1 and 3 estimation. Simulations of interlaboratory studies with unbalanced data and with small sample sizes do not show superiority of any of the possible combinations of estimation methods and Satterthwaite approaches on three measures of assay precision. However, the modified Satterthwaite approach with Henderson III Type 3 estimation is often preferred above the other combinations.