Article
Mathematics, Interdisciplinary Applications
Sara Dhaene, Yves Rosseel
Summary: This article investigates the estimation methods for Structural Equation Models (SEMs) and finds that the traditional Maximum Likelihood estimation suffers from finite sample bias, while Restricted Maximum Likelihood (REML) is only applicable to SEMs that are mathematically equivalent to mixed effect models. Through Monte Carlo simulations, it is discovered that resampling-based corrections such as Bootstrap and Jackknife effectively reduce small sample bias but increase variability. Similar conclusions are drawn for a proposed analytic approach by Ozenne et al., which is included for comparison.
STRUCTURAL EQUATION MODELING-A MULTIDISCIPLINARY JOURNAL
(2022)
Article
Social Sciences, Mathematical Methods
Xiaofeng Steven Liu
Summary: Eta squared is a commonly used effect size measure, but it tends to have positive bias. This paper introduces the use of bootstrapping to correct the bias in eta squared. Compared to other measures such as epsilon squared and omega squared, bootstrapped bias correction does not require specific distribution assumptions and is easily implemented. The application of this method is illustrated through a real example and computer simulations. The results show that the bootstrapped bias-corrected eta squared has minimal bias and can be a good alternative to eta squared and epsilon squared, especially in situations where epsilon squared can become negative.
METHODOLOGY-EUROPEAN JOURNAL OF RESEARCH METHODS FOR THE BEHAVIORAL AND SOCIAL SCIENCES
(2022)
Article
Engineering, Multidisciplinary
Daoming She, Minping Jia
Summary: This study introduces a RUL prediction method based on Bidirectional Gated Recurrent Unit (BiGRU), which calculates the confidence interval of RUL using the Bootstrap method. This approach reduces maintenance costs and has significant implications for production and manufacturing.
Article
Construction & Building Technology
Cheng Cui, Rokia Raslan, Ivan Korolija, Zaid Chalabi
Summary: This study investigates the impact of climate uncertainty on future thermal comfort and proposes the Bayesian bootstrap method to evaluate and compare the robustness of design alternatives. The results show that the nighttime overheating risk and variability in regulation-compliant dwellings are nearly 15 and 12 times greater than during the daytime, respectively. Adaptive ventilation is identified as a key measure to enhance the robustness of thermal comfort against climate uncertainty.
BUILDING AND ENVIRONMENT
(2022)
Article
Engineering, Mechanical
Adwait Sharma, C. S. Manohar
Summary: This paper investigates the evaluation of the reliability integral in the presence of complicating features of limit state functions. It proposes the use of particle splitting framework and an improved Markov chain Monte Carlo sampler with replica exchange strategy to enhance the detection and exploration of important regions of failure. The application of bootstrap technique to deduce the sampling variance of the estimator of the probability of failure is also developed. Several examples in structural mechanics are presented to compare the performance of the proposed method with existing methods.
PROBABILISTIC ENGINEERING MECHANICS
(2023)
Article
Psychology, Multidisciplinary
Tristan D. Tibbe, Amanda K. Montoya
Summary: This study proposes two alternative bias-correction methods for creating confidence intervals around the indirect effect. Comparisons with other methods using a Monte Carlo simulation show that these methods fall between the BCBCI and PBCI in terms of balance, power, and type I error rate. An extension of the simulation suggests that the increased power of these alternative methods might be due to their higher type I error rates. Therefore, the PBCI is still recommended if control over the type I error rate is desired for inference on the indirect effect.
FRONTIERS IN PSYCHOLOGY
(2022)
Article
Multidisciplinary Sciences
Yuyan Zheng, Yongfei Mao, Min Tsao, Laura L. E. Cowen
Summary: In this study, we introduce a new minimum chi-square method for estimating the size of a closed population using capture-recapture data. This method performs better than traditional likelihood methods under heterogeneous capture probabilities. Additionally, we develop two different bootstrap techniques that can be used with any underlying estimator for inferring population size.
Article
Environmental Sciences
Yi Wu, Chiyuan Miao, Xuewei Fan, Jiaojiao Gou, Qi Zhang, Haiyan Zheng
Summary: Decomposing the uncertainty of global climate models is crucial for understanding climate change. The study compares sources of uncertainty in temperature and precipitation projections from different phases of the Coupled Model Intercomparison Project and investigates the effectiveness of bias correction methods. The findings provide insights into model characteristics and offer decision-makers more accurate information for climate mitigation and adaptation measures.
Article
Engineering, Chemical
Takao Ueda, Tatsuya Oki
Summary: A simulation-based stereological correction method was developed to accurately estimate 3D composition distribution from measurable 2D composition distributions, with notable features including the requirement of relatively small input data and rapid analysis. Experimental validation showed high estimation accuracy for various types of particles, making it suitable for post analysis of SEM/EDX-based particle sectional liberation analysis.
MINERALS ENGINEERING
(2022)
Article
Mathematics
Xiaowen Dai, Shidan Huang, Libin Jin, Maozai Tian
Summary: This paper investigates the quantile regression for spatial panel data models with varying coefficients, which considers the changing impacts of covariates over time and location. Smoothing methods like B-spline and local polynomial approximation are used for approximating the varying coefficients. The fixed-effects quantile regression (FEQR) estimator is biased when there is a spatial lag variable, and the wild bootstrap method is employed to mitigate the bias. Simulations show that the proposed methods are stable and efficient, with the B-spline method outperforming the local polynomial approximation method, especially for location-varying coefficients. Real data on China's economic development are analyzed to demonstrate the application of the proposed procedure.
Article
Engineering, Mechanical
Weihao Su, Xintian Liu, Shen Xu, Jinbo Wang, Zhaoqiang Wang
Summary: Fatigue testing is crucial for assessing material and component fatigue performance, but it often faces uncertainties and small sample sizes. This paper proposes an improved bootstrap method to estimate uncertainties in small samples by addressing the limitations of traditional methods. The method was applied to estimate the effect of surface roughness and size on fatigue tests, resulting in improved estimation accuracy. The research contributes to the development of improved methods for fatigue life estimation, with practical implications for mechanical component design and optimization.
FATIGUE & FRACTURE OF ENGINEERING MATERIALS & STRUCTURES
(2023)
Article
Psychology, Multidisciplinary
Xiaofeng Steven Liu
Summary: Cohen's d has a positive bias and the traditional bias correction method based on strict distribution assumption may not always work for small studies with limited data. Non-parametric bootstrapping, which is not limited by distribution assumption, can be used to remove the bias in Cohen's d. A real example is provided to demonstrate the implementation of bootstrap bias estimation and the removal of sizable bias in Cohen's d.
JOURNAL OF GENERAL PSYCHOLOGY
(2023)
Editorial Material
Fisheries
William H. Satterthwaite
Summary: The broader scientific community is facing a reproducibility crisis due to various factors, including selective reporting and p-hacking, which may lead to false positive results and misleading effect size estimates. Fisheries science is also vulnerable to this issue, as bias can inadvertently enter the process through various decision-making steps. A simulation model demonstrates how asymmetric scrutiny of assessments or re-assessments can introduce bias into the advisory process for fishing limits in a multi-stock fishery.
FISHERIES RESEARCH
(2023)
Article
Multidisciplinary Sciences
Artur J. Lemonte
Summary: It is confirmed that the maximum likelihood estimators of the standard two-sided power distribution parameters introduced by van Dorp and Kotz can be biased. To address this issue in a parametric distribution, bootstrap bias correction methods are proposed. The study shows that the parametric bootstrap estimator, based on resampling, is favored. Real data applications further illustrate the effectiveness of bias correction for small sample sizes.
ADVANCED THEORY AND SIMULATIONS
(2023)
Article
Fisheries
Esther Schuch, Andries Richter
Summary: This study uses a database of fish stock assessments to investigate the presence of intuitive judgement, known as anchoring, in scientific advice. The findings suggest that anchoring is strongest in situations where model choices are flexible and the fish stock is in crisis, potentially increasing pressure and stakes.
FISH AND FISHERIES
(2022)
Article
Biodiversity Conservation
Andre E. Punt, Margaret C. Siple, Tessa B. Francis, Philip S. Hammond, Dennis Heinemann, Kristy J. Long, Jeff Moore, Maritza Sepulveda, Randall R. Reeves, Gudjon Mar Sigurdsson, Gisli Vikingsson, Paul R. Wade, Rob Williams, Alexandre N. Zerbini
Summary: The study addresses the challenge of determining acceptable rates of human-caused mortality in low-data situations for marine mammals and conservation species. Three alternative methods are developed to identify acceptable levels of human-caused mortality for long-lived, slowly reproducing species, using relative abundance indices and estimates of bycatch mortality in fisheries. The study shows that these methods can achieve conservation performance similar to the traditional PBR approach, but are more sensitive to uncertainties in estimating bycatch mortality.
JOURNAL OF APPLIED ECOLOGY
(2021)
Article
Green & Sustainable Science & Technology
Michael C. Melnychuk, Hiroyuki Kurota, Pamela M. Mace, Maite Pons, Coilin Minto, Giacomo Chato Osio, Olaf P. Jensen, Carryn L. de Moor, Ana M. Parma, L. Richard Little, Daniel Hively, Charmane E. Ashbrook, Nicole Baker, Ricardo O. Amoroso, Trevor A. Branch, Christopher M. Anderson, Cody S. Szuwalski, Julia K. Baum, Tim R. McClanahan, Yimin Ye, Alessandro Ligas, Jilali Bensbai, Grant G. Thompson, John DeVore, Arni Magnusson, Bjarte Bogstad, Edward Wort, Jake Rice, Ray Hilborn
Summary: Rebuilding plans and ratification of international fishing agreements were found to be the most effective management interventions in reducing overfishing and restoring biomass. Additionally, the benefits of management actions were cumulative, with improved stock status and increased predicted long-term catches as more measures were implemented.
NATURE SUSTAINABILITY
(2021)
Article
Fisheries
Cristian M. Canales, Andre E. Punt, Mauricio Mardones
Summary: This study introduces a Length-Based Pseudo-cohort Analysis (LBPA) model for estimating stock status in data-poor fisheries using multiple length-frequency samples, showing better performance compared to traditional methods. Simulations indicate that LBPA outperforms the length-based spawning potential ratio (LBSPR), especially under high exploitation rates.
FISHERIES RESEARCH
(2021)
Article
Fisheries
Catherine M. Dichmont, Roy A. Deng, Natalie Dowling, Andre E. Punt
Summary: Stock assessments are crucial for fisheries management, and there is a growing demand for assessments based on population dynamics models. The trend is shifting towards using flexible, documented software packages to improve efficiency and consistency. A website has been developed to collate available stock assessment packages and facilitate feedback between users and developers for designing the next generation of assessment tools.
FISHERIES RESEARCH
(2021)
Article
Fisheries
Cole C. Monnahan, James T. Thorson, Stan Kotwicki, Nathan Lauffenburger, James N. Ianelli, Andre E. Punt
Summary: Abundance indices from scientific surveys play a crucial role in stock assessment, but variations in fish availability over space and time can lead to inaccuracies. A vertically integrated index that considers spatiotemporal correlation and gear availability is essential for estimating more accurate indices for semi-pelagic fish species like walleye pollock. Understanding the spatial and temporal patterns in vertical distribution and gear availability is important for improving stock assessment methods.
ICES JOURNAL OF MARINE SCIENCE
(2021)
Article
Biodiversity Conservation
Cecilia A. O'Leary, Stan Kotwicki, Gerald R. Hoff, James T. Thorson, Vladimir V. Kulik, James N. Ianelli, Robert R. Lauth, Daniel G. Nichol, Jason Conner, Andre E. Punt
Summary: The study highlights the importance of intercalibrating disparate data to accurately index populations as they move beyond historical survey footprints. By combining US and Russian data, the research assesses changes in the availability of groundfish biomass in the Bering Sea, emphasizing the need for international cooperation on assessing spatial availability of stocks common to multiple countries.
JOURNAL OF APPLIED ECOLOGY
(2021)
Article
Oceanography
Andre E. Punt, Michael G. Dalton, Wei Cheng, Albert J. Hermann, Kirstin K. Holsman, Thomas P. Hurst, James N. Ianelli, Kelly A. Kearney, Carey R. McGilliard, Darren J. Pilcher, Matthieu Veron
Summary: Climate-enhanced stock assessment models integrate environmental variables into population dynamics models to better manage marine resources under climate change. These models can help calculate biological and economic reference points and projections under alternative harvest strategies.
DEEP-SEA RESEARCH PART II-TOPICAL STUDIES IN OCEANOGRAPHY
(2021)
Article
Fisheries
Tobias K. Mildenberger, Casper W. Berg, Alexandros Kokkalis, Adrian R. Hordyk, Chantel Wetzel, Nis S. Jacobsen, Andre E. Punt, J. Rasmus Nielsen
Summary: The study compares the effectiveness of two precautionary approaches in recovering over-exploited fish stocks, finding that both methods reduce the risk of overfishing at the expense of expected yield. The success of these strategies depends on HCRs, life-history parameters, and the level of scientific uncertainty.
FISH AND FISHERIES
(2022)
Article
Fisheries
Margaret C. Siple, Laura E. Koehn, Kelli F. Johnson, Andre E. Punt, T. Mariella Canales, Piera Carpi, Carryn L. de Moor, Jose A. A. De Oliveira, Jin Gao, Nis S. Jacobsen, Mimi E. Lam, Roberto Licandeo, Martin Lindegren, Shuyang Ma, Gudmundur J. Oskarsson, Sonia Sanchez-Marono, Szymon Smolinski, Szymon Surma, Yongjun Tian, Desiree Tommasi, Mariano T. Gutierrez, Verena Trenkel, Stephani G. Zador, Fabian Zimmermann
Summary: Management strategy evaluation (MSE) is a cutting-edge approach for testing and comparing management strategies, accounting for various uncertainties. Small pelagic fish play a vital ecological role in marine food webs, but present challenges to MSE and other evaluation methods due to their substantial ecological and life history uncertainties.
FISH AND FISHERIES
(2021)
Article
Oceanography
Georgina A. Gibson, Matthew R. Baker, William T. Stockhausen, Sarah Hinckley, Carolina Parada, Kerim Aydin, Kenneth O. Coyle, Albert J. Hermann, Thomas P. Hurst, Andre E. Punt
Summary: The Gulf of Alaska Integrated Ecosystem Research Program (GOAIERP) conducted a multi-disciplinary study to examine the influence of the environment on the survival and recruitment of early life stages of commercially and ecologically important groundfish species. The integration of Eulerian ecosystem models and Lagrangian Individual-Based Models provided valuable insights into recruitment processes and their potential application to fisheries management. However, coordination between model development, experimentation, and field sampling is challenging and requires careful consideration of data analysis and model validation.
DEEP-SEA RESEARCH PART II-TOPICAL STUDIES IN OCEANOGRAPHY
(2022)
Review
Fisheries
Daniel R. Goethel, Kristen L. Omori, Andre E. Punt, Patrick D. Lynch, Aaron M. Berger, Carryn L. de Moor, Eva E. Plaganyi, Jason M. Cope, Natalie A. Dowling, Richard McGarvey, Ann L. Preece, James T. Thorson, Milani Chaloupka, Sarah Gaichas, Eric Gilman, Sybrand A. Hesp, Catherine Longo, Nan Yao, Richard D. Methot
Summary: Marine population modeling is an important research field that supports fisheries interventions. It has made recent advancements to address challenges like climate change and enduring issues such as data limitations. The review highlights the integration of various dimensions in fisheries models, facilitated by interdisciplinary research teams and improved data collection protocols. However, the implementation of model-based advice and sharing of confidential data remain challenges. The authors recommend participatory co-management approaches, wider inclusion of local knowledge and stakeholder input, and improved communication and engagement in fisheries management to make better informed decisions.
REVIEWS IN FISH BIOLOGY AND FISHERIES
(2023)
Article
Fisheries
Sean Pascoe, Andre E. Punt, Trevor Hutton, Paul Burch, Pia Bessell-Browne, L. Richard Little
Summary: Consideration of economic outcomes is common in fisheries management globally, but few jurisdictions prioritize economic objectives. Australia's federally managed fisheries have adopted maximum economic yield (MEY) as their primary objective, with biomass-based target reference points used in harvest control rules. In the absence of explicit estimates for biomass-based MEY (BMEY), proxy estimates based on maximum sustainable yield (BMSY) are used. However, estimating BMEY in multi-species fisheries is challenging due to assessments conducted at the individual species level, while economic activity spans across species. This complexity is further compounded in fisheries with multiple fishing gears and targeting practices. Using an age-structured bioeconomic model, this study estimates BMEY for key species in a multi-species, multi-metier fishery, revealing higher optimal biomass levels compared to the current proxy-based system, with economic targets sensitive to changing prices and fishing costs.
CANADIAN JOURNAL OF FISHERIES AND AQUATIC SCIENCES
(2023)
Article
Fisheries
A. Gunnarsson, J. Kennedy, A. Magnusson, B. Bardarson, B. Elvarsson
Summary: Oocyte size and weight in Atlantic wolffish (Anarhichas lupus) and spotted wolffish (Anarhichas minor) were studied after fixation and storage in formalin. The effect of formalin on oocyte size varied depending on the original size of the oocyte. A formula was developed to convert fixed oocyte size/weight to fresh oocyte size/weight. The relationships were found to be negative and nonlinear, with smaller oocytes increasing in size and weight after fixation, while larger oocytes decreased.
FISHERIES RESEARCH
(2023)
Article
Fisheries
Cody S. Szuwalski, Anne B. Hollowed, Kirstin K. Holsman, James N. Ianelli, Christopher M. Legault, Michael C. Melnychuk, Dan Ovando, Andre E. Punt
Summary: Climate change can impact global fisheries productivity. Maintaining current management targets is more beneficial for biodiversity protection than increasing catch through climate adaptation in maximum sustainable yield (MSY) based management. The conservation gain of maintaining management targets increases as the harmful impacts of climate change on productivity worsen. New management tools are needed to balance conservation and food production in ecosystems with non-stationary productivity.
FISH AND FISHERIES
(2023)
Article
Biodiversity Conservation
A. J. Warlick, G. K. Himes Boor, T. L. McGuire, K. E. W. Shelden, E. K. Jacobson, C. Boyd, P. R. Wade, A. E. Punt, S. J. Converse
Summary: Knowledge about demographic and environmental factors is crucial for designing effective conservation measures. This study used an integrated population model to analyze the endangered Cook Inlet population of beluga whales. The research revealed possible depression in survival and fecundity, and predicted a continued decline with a 17-32% probability of extinction in 150 years. The study highlights the usefulness of integrated population modeling in understanding population dynamics and identifying factors contributing to the failure of protected populations to recover.
ANIMAL CONSERVATION
(2023)