Academic literature on the topic 'Residual maximum likelihood method (REML)'

The study was conducted in five locations i.e Kediri, Ponorogo, Probolinggo, Malang, and Mojokerto, from November 2010 until August 2011. The planting materials used were 15 cassava clones. The research objective was to compare analysis methods of the genotype × environment interaction, namely: a) GGE technique using REML without A matrix by assuming homogeneous residual error variance, b) GGE technique using REML with A matrix by assuming homogeneous residual error variance, c) GGE technique using REML without A matrix by assuming heterogeneous residual error variance, and d) GGE technique using REML with A matrix by assuming heterogeneous residual error variance. The results showed that GGE technique using REML without A matrix by assuming heterogeneous residual error variance was more appropriate. Clones CMM 03038-7 (G8) had a wide adaptability and high yield potential, and its clone was closest to the ideal criteria for genotype compared with other genotypes. Clones CMM 03094-4 (G10) had specific adaptability in the environments S2 (Malang) and S5 (Mojokerto), and it had higher yield potential than the control varieties UJ5, Malang 6, and Adira 4. Environment Kediri (S1) had the highest yield among other environments and Kediri was a suitable environment for the growth and selection of cassava.<p align="center"> </p>

Abstract. A multi-trait repeatability animal model under restricted maximum likelihood (REML) and Bayesian methods was used to estimate genetic parameters of milk, fat, and protein yields in Tunisian Holstein cows. The estimates of heritability for milk, fat, and protein yields from the REML procedure were 0.21 ± 0.05, 0.159 ± 0.04, and 0.158 ± 0.04, respectively. The corresponding results from the Bayesian procedure were 0.273 ± 0.02, 0.198 ± 0.01, and 0.187 ± 0.01. Heritability estimates tended to be larger via the Bayesian than those obtained by the REML method. Genetic and permanent environmental variances estimated by REML were smaller than those obtained by the Bayesian analysis. Inversely, REML estimates of the residual variances were larger than Bayesian estimates. Genetic and permanent correlation estimates were on the other hand comparable by both REML and Bayesian methods with permanent environmental being larger than genetic correlations. Results from this study confirm previous reports on genetic parameters for milk traits in Tunisian Holsteins and suggest that a multi-trait approach can be an alternative for implementing a routine genetic evaluation of the Tunisian dairy cattle population.

SummaryTwo scries of simulation experiments were used to investigate the accuracy of treatment and variance estimation with a neighbour analysis of field trials proposed by Gleeson & Cullis (1987). The first series examined the accuracy of residual maximum likelihood (REML) estimation of seven theoretical error models applicable to field trials. REML estimation provided accurate estimates of the variance parameters, but the Ftest of treatments was slightly biased upward (to +2·4%) for first differences models and slightly biased downwards (to –1·4%) for second differences models. The second series of simulations, based on 19 uniformity data sets, illustrated that treatment effects were consistently estimated more accurately by the REML neighbour (RN) analysis of Gleeson & Cullis (1987) than by incomplete block (IB) analysis with recovery of interblock information. The relative gain in accuracy of RN over IB depends on the amount of systematic variation or ‘trend’ in the trial, and ranged from 6 to 18% with an average of 12% for a range of trend and error variances commonly encountered in field trials. The predicted average standard errors of pairwise treatment differences from the RN analysis were in close agreement with their empirical estimates, indicating that the predicted average S.E.D. is approximately valid.

The purpose of this study was to select top cross hybrids of green maize for yield, derived from partially inbred S1 lines based on genetic values using the REML/Blup method, and to estimate important genetic parameters for green maize breeding programs. The experiment was conducted in an experimental area located between 17º53´ S and 52º43´ W, 680 m altitude. The evaluation of 75 top cross hybrids was performed in a randomized block design with four replicates. A sample of five plants/ears was used in each plot to evaluate grain mass trait (MASS). For commercial ear yield trait (CEYIELD), evaluations were carried out for the total number of plants per plot. Hybrids were selected via BLUP procedures using the Selegen-REML/Blup program. Based on the Restricted Maximum Likelihood (REML), we estimated the coefficients of genetic and residual variation and components of variance, by which a genetic variability between the top cross hybrids was observed. This shows the possibility of successful selection for the traits under evaluation. The estimated accuracy for the selection of top cross hybrids was 0.81 for commercial ear yield and 0.64 for grain mass, pointing to high and moderate precision levels for CEYIELD and MASS traits, respectively, corroborating the possibility of success in selecting top cross hybrids based on the CEYIELD trait. The predicted genetic gain from the selection was 20.12%, for CEYIELD, and 6.10%, for MASS. Therefore, the REML/Blup statistical tool was efficient in selecting top cross hybrids of green maize, providing significant genetic gains for the traits under evaluation. There was evidence that hybrids 19 and 48 were distinguished from others because of the high genetic effects obtained for the commercial ear yield and grain mass weight.

Statistical methods to map quantitative trait loci (QTL) in outbred populations are reviewed, extensions and applications to human and plant genetic data are indicated, and areas for further research are identified. Simple and computationally inexpensive methods include (multiple) linear regression of phenotype on marker genotypes and regression of squared phenotypic differences among relative pairs on estimated proportions of identity-by-descent at a locus. These methods are less suited for genetic parameter estimation in outbred populations but allow the determination of test statistic distributions via simulation or data permutation; however, further inferences including confidence intervals of QTL location require the use of Monte Carlo or bootstrap sampling techniques. A method which is intermediate in computational requirements is residual maximum likelihood (REML) with a covariance matrix of random QTL effects conditional on information from multiple linked markers. Testing for the number of QTLs on a chromosome is difficult in a classical framework. The computationally most demanding methods are maximum likelihood and Bayesian analysis, which take account of the distribution of multilocus marker-QTL genotypes on a pedigree and permit investigators to fit different models of variation at the QTL. The Bayesian analysis includes the number of QTLS on a chromosome as an unknown.

Abstract In this paper, we introduce a new two-parameter lifetime distribution which is called extended Half-Logistic (EHL) distribution. Theoretical properties of this model including the hazard function, quantile function, asymptotic, extreme value, moments, conditional moments, mean residual life, mean past lifetime, residual entropy, cumulative residual entropy and order statistics are derived and studied in details. The maximum likelihood estimates of parameters are compared with various methods of estimations by conducting a simulation study. Finally, two real data sets are illustration the purposes.

AbstractWhen the univariate twin design is extended by including parents of twins, it is possible to assess additive genetic effects in the presence of assortative mating and genotype-environment correlation, the effects of parental influence, as well as the extent of residual shared environmental influences. The analysis of data obtained in such an extended twin design can be carried out by means of constrained maximum likelihood confirmatory factor analysis. Specifically, the structural model underlying this design can be represented as a LISREL model with nonlinear constraints. This representation offers the possibility to consider extended multivariate twin designs involving common genetic and environmental factors. The proposed method will be illustrated with applications to simulated and real data.

This paper proposed a new probability distribution, namely, the half-logistic xgamma (HLXG) distribution. Various statistical properties, such as, moments, incomplete moments, mean residual life, and stochastic ordering of the proposed distribution, are discussed. Parameter estimation of the half-logistic xgamma distribution is approached by the maximum likelihood method based on complete and censored samples. Asymptotic confidence intervals of model parameters are provided. A simulation study is conducted to illustrate the theoretical results. Moreover, the model parameters of the HLXG distribution are estimated by using the maximum likelihood, least square, maximum product spacing, percentile, and Cramer–von Mises (CVM) methods. Superiority of the new model over some existing distributions is illustrated through three real data sets.

Despite recent efforts to characterize the uncertainties involved with geological profiles and soil and rock properties, there has been limited study on their spatial correlations and how such features may be included in the engineering decision-making process. This paper presents an integrated framework for geostatisical analyses, which incorporates the restricted maximum likelihood (REML) method with the Matérn autocovariance model. Statistical tests are conducted including those for data normality, constant variance, and outliers, which ensure the fundamental assumptions of REML are not violated in the residual analyses of site data, meanwhile offering simple checks for potential errors in the dataset. The proposed approach also allows quantification of uncertainties in the subsurface profiles at the unsampled locations. The approach is illustrated through investigations on spatial correlation features of geological profiles at two project sites in Hong Kong. The number of irregularly spaced boreholes varies from 150 to 350 in the two cases, and the large volume of data enables the variations in rockhead levels to be studied through the proposed framework. In addition, the existence of geological faults in one of the sites is found to significantly affect the spatial variability of the rockhead level, as indicated by the reduced scales of fluctuation and spatial dependence, which corresponds to increased uncertainty in areas intersected by faults.

Seven agroforestry (AF) systems namely Eucalyptus grandis Hill ex Maiden (flooded gum, E), Dendrocalamus latiflorus Munro (Ma bamboo, B) and Digitaria decumbens Stent (Pangola, P), and their mixed plantations (BE, BP, EP, BEP) were monitored during the initial two years of growth for their efficiency in effluent removal. The municipal effluent irrigated plantation trial was established on a 1.6 ha site in the Capricornia coastal region at Yeppoon, Queensland in June 2002. This site was monitored until June 2004 for changes in site hydrology, physical, chemical and microbial properties of soil, and for plant growth, biomass production and nutrient uptake. The residual maximum likelihood method (REML) and analysis of variance (ANOVA) were extensively used to statistically compare the changes.

The plantations were irrigated at a modelled conservative irrigation rate of 1.42 ML ha^-1yr^-1. The total water use of all the AF systems was four to six times of that provided via irrigation. The mixed AF systems used more water than monoculture AF systems. During the initial two years, all the AF systems were effective in utilising effluent (both water and nutrients) due to the presence of groundflora. Over time, the efficiency and total water use may decline with reduction in groundflora and photosynthetically active canopy.

The vegetation of these AF systems accumulated six to ten times the major nutrients supplied via effluent irrigation. However, the AF systems with the exception of the E system failed to take up the supplied sodium and sulphur. Progressive build up of sodium in the soil would introduce sodicity in the soil and this may restrict the long term use of effluent disposal site. The electrical conductivity (EC_1.5) increased significantly in upper two soil layers whereas exchangeable sodium, CEC and ESP significantly increased over time in all the soil layers. Although soil compaction, reduction in infiltration rate, and increase in electrical conductivity and exchangeable sodium were observed at the site, the current changes did not indicate any ecological degradation. A long term study may help determine the optional rotation age of the AF crops to avoid adverse impact to the site.

Although the build up of microbiota in the effluent irrigated site increased considerably in all the AF systems, it did not reveal any health hazard. A study in mortality rates of different enteric bacteria indicated that the pathogens died within 15 days in winter and in less than 27 days in summer upon cessation of irrigation. Restricting access to the effluent irrigated site for up to 30 days would reduce the probability of a human health hazard due to the effluent irrigation.

At the conservative rate of irrigation (1.42 ML ha^-1yr^-1), the plantations produced up to 72 tonne biomass ha^-1 (dry biomass) within 24 months. Largely, the biomass produced in the AF systems was non-woody, thus it would need non-conventional markets. Leaves were the major site of nutrient storage. Senescence of leaves and twigs may accelerate nutrient recycling and this may defeat the objective of effluent irrigation. Moreover, the plants were selective in nutrient sequestering. Not more than one kg ha^-1 of any micro-nutrients was accumulated by bamboo and groundflora. For sustainability of effluent irrigation, the plantations may have to be either harvested in short rotation or irrigation has to be regulated according to plant growth. The commercial viability of the biomass produced in the AF systems was assessed to determine local suitability of the plantation models.

Canonical variate analysis (CVA), a type of multiple variate analysis, based on the combined data of various parameters showed differences between AF systems. These differences are likely to diverge with age of the plantations. The CVA based on more than four parameters showed differences amongst the AF systems. Moreover, the CVA for the datasets of some parameters collected at different time also revealed divergence amongst the AF systems. The analysis showed that the AF systems may develop contrasting differences with maturity. Monoculture E plantation produced more biomass than other AF systems, and it also accumulated more nutrients, compared to mixed AF systems. In contrast mixed AF systems (e.g., BP and BE) used more water than the monoculture systems. Overall, at 24 months, the mixed AF systems prove to offer improved benefits for effluent irrigation in terms of technical feasibility, ecological safety, and commercial viability of the effluent irrigated plantations.

Methodology is developed for Quantitative Trait Loci (QTL) analysis in F₂ and backcross designed experiments between outbred lines using a mixed model framework through the modification of segment mapping techniques. Alleles are modelled in the F₁ and parental generations allowing the estimation of individual additive allele effects while accounting for QTL segregation within lines as well as differences in mean QTL effects between lines.

Initially the theory, called F₁ origin mapping, is developed for a single trait scenario involving possible multiple QTL and polygenic variation. Additive genetic variances are estimated via Restricted Maximum Likelihood (REML) and allele effects are modelled using Best Linear Unbiased Prediction (BLUP). Simulation studies are carried out comparing F₁ origin mapping with existing segment mapping methods in a number of genetic scenarios. While there was no significant difference in the estimation of effects between the two methods the average CPU time of one hundred replicates was 0.26 seconds for F₁ origin mapping and 3.77 seconds for the segment mapping method. This improvement in computation efficiency is due to the restructuring of IBD matrices which result in the inversion and REML iteration over much smaller matrices.

Further theory is developed which extends F₁ origin mapping from single to multiple trait scenarios for F₂ crosses between outbred lines. A bivariate trait is simulated using a single QTL with and without a polygenic component. A single trait and bivariate trait analysis are performed to compare the two approaches. There was no significant difference in the estimation of QTL effects between the two approaches. However, there was a slight improvement in the accuracy of QTL position estimates in the multiple trait approach. The advantage of F₁ origin mapping with regard to computational efficiency becomes even more important with multiple trait analysis and allows the investigation of interesting biological models of gene expression.

F₁ origin mapping is developed further to model the correlation structure inherent in repeated measures data collected on F₂ crosses between outbred lines. A study was conducted to show that repeated measures F₁ origin mapping and multiple trait F₁ origin mapping give similar results in certain circumstances. Another simulation study was also conducted in which five regular repeated measures where simulated with allele breed difference effects and allele variances increasing linearly over time. Various polynomial orders of fit where investigated with the linear order of fit most parsimoniously modelling the data. The linear order of fit correctly identified the increasing trend in both the additive allele difference and allele variance. Repeated measures F₁ origin mapping possesses the benefits of using the correlated nature of repeated measures while increasing the efficiency of QTL parameter estimation. Hence, it would be useful for QTL studies on measurements such as milk yield or live weights when collected at irregular intervals.

Theory is developed to combine the data from QTL studies involving F₂ and backcross designed experiments. Genetic covariance matrices are developed for random QTL effects by modelling allele variation in the parental generation instead of the offspring generation for an F₂ and backcross between outbred lines. The result is a general QTL estimation method called parental origin mapping. Phenotypes and genotypes from such a study involving Romney and Merino sheep are analysed providing evidence for a QTL affecting adult and hogget fibre diameter.

By coupling these new methods with computer software programs such as ASREML, F₁ origin mapping and parental origin mapping provide powerful and flexible tools for QTL studies with the ability to efficiently handle single traits, multiple traits and repeated measures.

<p>Using a multi-objective optimization algorithm avoid the use of weighting factors to balance the different residuals in a finite element model updating procedure under the maximum likelihood method. By using this approach, the fittest model is not unique and a set of solutions that form a curve, so-called Pareto optimal front, is obtained. Within this paper, first a review of the state of the art on the criteria used to determine the most adequate model among all the solutions of the Pareto front is presented. Subsequently, a case study of a real footbridge is considered. A finite element model of the footbridge is updated based on its experimental modal parameters. The Non- Dominated Sorting Genetic Algorithm is used to obtain the Pareto front. Since all the solutions in the Pareto front are non-dominated, the selection of the best candidate requires a reasonable criterion. Herein, different procedures to select the best updated model are discussed.</p>

This paper presents a 5-axis machine tool compensation method that uses tool tip measurements recorded throughout the joint space to construct a set of compensation tables. The measurements can be taken using a laser tracker, permitting rapid measurement at most locations in the joint space. To compensate the machine tool, the measurements are used to identify a kinematic model, and then that model is used to construct an optimal set of compensation tables. The kinematic model is composed of the nominal, or ideal, kinematics with additional (unknown) six degree of freedom errors inserted between each of the joints. The error kinematics are identified using the measurement data and a maximum likelihood estimator. The identified model is then projected onto a joint-compensation space that maps to the compensation tables in the machine tool controller. Simulations of the approach are provided using measurement data from a Flow International 5-axis machine tool equipped with a Siemens 840D controller. The simulation results show a mean residual error of .076 mm, which is a 76.8% reduction from the uncalibrated machine tool.

Flow accelerated corrosion (FAC) is a major degradation form of carbon steel and low alloy pipes in the secondary circuit of pressurized water reactor (PWR) plants, which has great impact on plant safety and reliability. For the purpose of effectively monitoring FAC in nuclear power plants, a statistical model for accessing FAC wall thinning rate using plant inspection data is proposed in this paper. The presented model is developed based on Gaussian stochastic process models. Wall thinning rate is considered as a function of key factors that have important influence on the FAC process (i.e., temperature, pH, mass transfer coefficient, etc.). The Kriging method, which has been widely applied in the domain of spatial analysis, is used to model the relationship between wall thinning rate and its impact factors. Model parameters are determined through maximum likelihood estimation using the inspection data. Since the likelihood function of the Kriging model is usually complicated in form, the genetic algorithm is employed to find parameter values that maximize this function. From the presented model, residual lifetime distributions of pipes affected by FAC can be derived, and conditions that may lead to high FAC rate can be found, which provides decision-making support for maintenance strategies optimization in life cycle management of the feed water system. Wall thinning data simulated from a physical-chemical mechanism model presented in literature are used to verify the presented model. Results of validation show that reasonable wall thinning rates and lifetime distributions can be obtained using this model.

Abstract In regions with high intermittent renewable energy share, thermal plants are forced to operate with greater flexibility beyond their original design intent. Decreasing energy prices and capacity factors will further force these plants to more transient operation with steeper load gradients. Older steam turbine (ST) protections systems on site are often not designed for such flexible operation and do not properly supervise the resulting impact on lifetime consumption. Therefore, precise lifetime management concepts are required to increase plant reliability and flexibility, and to mitigate risks for new implemented operation modes. Several lifetime assessment methods were developed to quantify the damage evolution and the residual lifetime for ST components. Usually, these methods require both input about representative or operated loading profiles as well as characteristic material curves. These characteristic curves are determined by a number of standardized material tests. Due to the material scatter and other different sources of uncertainties, each test is a realization of a stochastic process. Hence, the corresponding characteristic material curves inherit these uncertainties and do not represent an absolute limit. The analyses of different loading profiles even for the same plant and same start-up class reveal that the consideration of statistically evaluated specific start-up distributions and further transient events are of major importance. Probabilistic methods are able to quantify all of these uncertainties and compute the probability of failure for a given lifetime or vice versa. Within this paper, at first an extensive and systematic operational profile analysis is carried out and discussed, which acts as an input for a probabilistic lifetime assessment approach. For that, a developed probabilistic workflow is presented to quantify the uncertainties and for lifetime prediction using the generalized damage accumulation rule with focus on creep-fatigue loading. To quantify the characteristic material curves, existing experimental data of a 2%-Cr forged steel (23CrMoNiWV8-8) is used. A probabilistic representation of the Wilshire-Scharning equation characterizes the creep rupture behavior. The maximum-likelihood method is used for parameter estimation and to take still running long term creep experiments into account. The end of life in low cycle fatigue experiments is characterized by a macroscopic crack initiation and the Manson-Coffin-Basquin equation is utilized to represent the characteristic material curve. A temperature modified version of the Manson-Coffin-Basquin equation is used to represent the experimental data. The parameter estimation is done by using the linear regression analysis followed by a comprehensive regression diagnostic. Taking both, the material and the load scatter into account, a reliability analysis is carried out to compute the probability of crack initiation. Finally, different load cases are considered and evaluated against each other.