Bootstrapping data with multiple levels of variation

Field, Chris; Pang, Zhen; Welsh, A. H.

doi:10.1002/cjs.5550360403

Cited by 17 publications

(12 citation statements)

References 8 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also applied a studentized bootstrap, which gave similar results but required more computation time [56], [57], [58]. All the analyses were performed with SAS version 9.2.…”

Section: Methodsmentioning

confidence: 99%

Uniform Selection as a Primary Force Reducing Population Genetic Differentiation of Cavitation Resistance across a Species Range

et al. 2011

View full text Add to dashboard Cite

BackgroundCavitation resistance to water stress-induced embolism determines plant survival during drought. This adaptive trait has been described as highly variable in a wide range of tree species, but little is known about the extent of genetic and phenotypic variability within species. This information is essential to our understanding of the evolutionary forces that have shaped this trait, and for evaluation of its inclusion in breeding programs.MethodologyWe assessed cavitation resistance (P 50), growth and carbon isotope composition in six Pinus pinaster populations in a provenance and progeny trial. We estimated the heritability of cavitation resistance and compared the distribution of neutral markers (F ST) and quantitative genetic differentiation (Q ST), for retrospective identification of the evolutionary forces acting on these traits.Results/DiscussionIn contrast to growth and carbon isotope composition, no population differentiation was found for cavitation resistance. Heritability was higher than for the other traits, with a low additive genetic variance (h2 ns = 0.43±0.18, CVA = 4.4%). Q ST was significantly lower than F ST, indicating uniform selection for P 50, rather than genetic drift. Putative mechanisms underlying QST

show abstract

“…We also applied a studentized bootstrap, which gave similar results but required more computation time [56], [57], [58]. All the analyses were performed with SAS version 9.2.…”

Section: Methodsmentioning

confidence: 99%

Uniform Selection as a Primary Force Reducing Population Genetic Differentiation of Cavitation Resistance across a Species Range

et al. 2011

View full text Add to dashboard Cite

show abstract

“…On the other hand, our bootstrap is similar to that of Carpenter, Goldstein, and Rasbash () or Field et al (, ), who examined the so‐called random effects bootstrap in classical statistics. We go further by demonstrating the validity of the bootstrap for both the ML estimates of the mixed linear model (see theorem 2) and for a more general and complex parameter, which is the robust estimator of the small‐area mean or total.…”

Section: The Mse Bootstrap Estimatormentioning

confidence: 56%

“…Assumption 2 states that the ratio of the number of areas over the total number of observations is asymptotically a constant fraction. This condition is weaker than the one required by Field, Pang, and Welsh (2008) to establish the validity of the random-effect bootstrap (for linear mixed models). Field et al (2008) require that each of the area's sample size converges to infinity as the number of areas increases.…”

Section: Asymptotic Properties Of the Robust Parameter Estimatormentioning

confidence: 87%

“…This condition is weaker than the one required by Field, Pang, and Welsh (2008) to establish the validity of the random-effect bootstrap (for linear mixed models). Field et al (2008) require that each of the area's sample size converges to infinity as the number of areas increases. In contrast, in our framework, all the areas could remain small as the number of areas increases.…”

Section: Asymptotic Properties Of the Robust Parameter Estimatormentioning

confidence: 87%

See 1 more Smart Citation

Bootstrapping mean‐squared errors of robust small‐area estimators: Application to the method‐of‐payments surveys data

Jiongo

Nguimkeu

2019

Scandinavian J Statistics

View full text Add to dashboard Cite

This paper proposes a new bootstrap procedure for mean‐squared errors of robust small‐area estimators. We formally prove the asymptotic validity of the proposed bootstrap method and examine its finite‐sample performance through Monte Carlo simulations. The results show that our procedure performs well and competes with existing ones. We also provide an application to the estimation of the total volume and value of cash, debit card, and credit card transactions in Canada as well as in its provinces and subgroups of households. In particular, we found that there is a significant average annual decline rate of 3.1% in the volume of cash transactions and that this decline is relatively higher among high‐income households living in heavily populated provinces. Our bootstrap estimator also provides indicators of quality useful in selecting the best small‐area predictor among several alternatives in practice.

show abstract

“…This proposal is then compared to adaptations of other schemes such as the so-called Random Effect Bootstrap (REB), see e.g. Davison & Hinkley (1997); Carpenter et al (2003); Field et al (2008) and the more widespread PB alternatives.…”

Section: Introductionmentioning

confidence: 99%

Bootstrap estimation of uncertainty in prediction for generalized linear mixed models

Flores-Agreda

Cantoni

2019

Computational Statistics & Data Analysis

View full text Add to dashboard Cite

In this article, we focus on the estimation of the Mean Squared Error for the Predictors (MSEP) of Random Effects (RE) in Generalized Linear Mixed Models (GLMM) by means of non-parametric bootstrap methods. In the frequentist paradigm, the MSEP is used as a measure of the uncertainty in prediction and has been shown to be affected by the estimation of the model parameters. In the particular case of linear mixed models (LMM), two solutions are provided to practitioners: on one hand, secondorder correct approximations which yield estimators of this quantity and, on the other hand, several Parametric Bootstrap algorithms. We propose a non-parametric bootstrap scheme, consisting of an adaptation of the Random Weighted Laplace Bootstrap (RWLB) that can be used in the entire class of GLMM. On a first stage, the RWLB is used to generate bootstrap replicates of the parameters while, on a second stage, simulation is used to generate bootstrap samples of standardized RE. We conduct a first simulation study in the framework of Gaussian LMM to contrast the quality of our approach with respect to: (i) analytical estimators of MSEP based on approximations, (ii) Conditional Variances obtained with a Bayesian representation and (iii) other bootstrap schemes, on the grounds of their relative bias, relative efficiency and the coverage ratios of resulting prediction intervals. A second simulation study serves the purpose to illustrate the use and benefits of our proposal against other feasible alternatives in a pure, Non-Gaussian, GLMM setting.

show abstract

Bootstrapping data with multiple levels of variation

Cited by 17 publications

References 8 publications

Uniform Selection as a Primary Force Reducing Population Genetic Differentiation of Cavitation Resistance across a Species Range

Uniform Selection as a Primary Force Reducing Population Genetic Differentiation of Cavitation Resistance across a Species Range

Bootstrapping mean‐squared errors of robust small‐area estimators: Application to the method‐of‐payments surveys data

Bootstrap estimation of uncertainty in prediction for generalized linear mixed models

Contact Info

Product

Resources

About