Article
Psychology, Multidisciplinary
Min Lu
Summary: Multivariate meta-analysis (MMA) is a powerful statistical technique that provides more reliable and informative results than traditional univariate meta-analysis. The metavcov package offers tools for model preparation, data visualization, and missing data solutions, which are not available in accessible software. It allows users to compute various types of effect sizes and their variance-covariance matrices, and provides tools for plotting confidence intervals and handling missing data through imputation methods.
FRONTIERS IN PSYCHOLOGY
(2023)
Article
Mathematical & Computational Biology
Jon A. Steingrimsson, David H. Barker, Ruofan Bie, Issa J. Dahabreh
Summary: Causally interpretable meta-analysis is used to estimate treatment effects in a target population with missing covariate data. This article provides identification results for potential outcome means and average treatment effects, and proposes three estimators with good performance. Lung cancer screening trial data and NHANES population data are analyzed using the estimators, with modifications for survey design.
Article
Ecology
Shinichi Nakagawa, Daniel W. A. Noble, Malgorzata Lagisz, Rebecca Spake, Wolfgang Viechtbauer, Alistair M. Senior
Summary: The log response ratio (lnRR) is commonly used in ecology meta-analysis, but missing standard deviations (SDs) pose a challenge in estimating the sampling variance. We propose a new method using weighted average coefficient of variation (CV) from studies reporting SDs to address this issue. Our results show that using the average CV to estimate sampling variances for all observations, regardless of missingness, performs better than the conventional approach using individual study-specific CV with complete data. This approach is broadly applicable and can be implemented in all lnRR meta-analyses.
Article
Statistics & Probability
Hejian Sang, Jae Kwang Kim, Danhyang Lee
Summary: This article proposes a novel method of semiparametric fractional imputation (SFI) using Gaussian mixture models to handle missing data. The proposed method is computationally efficient and leads to robust estimation. Simulation studies are conducted to validate the performance of the proposed method.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2022)
Article
Computer Science, Interdisciplinary Applications
Maria Luz Gamiz, Enno Mammen, Maria Dolores Martinez-Miranda, Jens Perch Nielsen
Summary: The paper discusses a strategy for addressing a new missing data issue in survival analysis, using iterative nonparametric techniques to estimate and utilize missing data information for further estimation in each step. The theoretical framework is established and simulations demonstrate good performance with finite samples. The primary motivation is the application to French Covid-19 patient data on hospitalizations over time.
COMPUTATIONAL STATISTICS & DATA ANALYSIS
(2022)
Article
Engineering, Mechanical
Carlos E. N. Mazzilli, Paulo B. Goncalves, Guilherme R. Franzini
Summary: This paper provides a detailed literature review on non-linear modes of vibration and their role in obtaining more efficient reduced-order models compared to those obtained by Galerkin's method using classical linear modes. It presents a chronological development of definitions, properties, evaluation methods, and applications of non-linear modes to engineering problems, from Poincare to Liapunov, from Rosenberg and Vakakis to Shaw and Pierre, covering the past to present progress in this field.
INTERNATIONAL JOURNAL OF MECHANICAL SCIENCES
(2022)
Review
Clinical Neurology
Sophie B. Haywood, Penelope Hasking, Mark E. Boyes
Summary: Non-suicidal self-injury (NSSI) refers to intentional and deliberate damage to an individual's own body tissue without the intent to suicide. Individuals with higher levels of experiential avoidance are more likely to have a history of NSSI. This study systematically reviewed and meta-analyzed studies examining the associations between experiential avoidance and self-injury.
JOURNAL OF AFFECTIVE DISORDERS
(2023)
Article
Computer Science, Artificial Intelligence
Chen Kong, Simon Lucey
Summary: The paper introduces a novel hierarchical sparse coding model to overcome limitations of current NRSfM algorithms in terms of image quantity and shape variability handling. By training an unsupervised deep neural network auto-encoder, the approach achieves impressive precision and robustness in solving NRSfM problems.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Ecology
Ozan Cinar, Shinichi Nakagawa, Wolfgang Viechtbauer
Summary: Meta-analyses in ecology and evolution require special attention due to unique study characteristics in these fields. Results from studies with different species violate the independence assumption, and multiple effect sizes present challenges for conventional meta-analytic models. Simulation studies suggest that only complex multilevel models that account for species-level variance provide unbiased estimates in such analyses.
METHODS IN ECOLOGY AND EVOLUTION
(2022)
Article
Health Policy & Services
Sadaf Kabir, Leily Farrokhvar
Summary: The availability of data in healthcare allows for the discovery of new patterns and improvement in clinical decision making. However, missing values in medical data can impact predictive models. This study proposes modified autoencoder models for data imputation and demonstrates their superiority through experiments.
HEALTH CARE MANAGEMENT SCIENCE
(2022)
Article
Economics
Jennifer L. Castle, Jurgen A. Doornik, David F. Hendry
Summary: This passage discusses methods for handling fat big data, including using principal components analysis and equilibrium correction models to identify cointegrating relations, and using saturation estimation to handle non-stationary fat data. When dealing with a large number of potentially spurious connections, it is important to seek substantive relationships, and big data can be useful if they help ensure that the data generation process is nested in the model.
INTERNATIONAL JOURNAL OF FORECASTING
(2021)
Article
Medicine, General & Internal
Loukia M. Spineli, Chrysostomos Kalyvas, Katerina Papadimitropoulou
Summary: This study investigates the prevalence of robust conclusions in systematic reviews addressing missing outcome data and compares them with current sensitivity analysis standards. The study found that studies with significant missing outcome data tend to have more frail conclusions. The newly proposed robustness index (RI) indicates that a considerable proportion of analyses fail to demonstrate robustness compared to when using current sensitivity analysis standards.
Article
Engineering, Civil
Tomasz Niedzielski, Michal Halicki
Summary: This study proposes a method that combines linear interpolation with autoregressive integrated model (ARI) to handle missing hydrological data. The method, named LinAR, outperforms the purely linear method, especially for short no-data gaps and rivers of considerable size. The LinAR method contributes to the current state of art in gap-filling methods by removing artificial jumps and introducing irregular variability in the filled data.
WATER RESOURCES MANAGEMENT
(2023)
Article
Computer Science, Artificial Intelligence
C. G. Marcelino, G. M. C. Leite, P. Celes, C. E. Pedreira
Summary: This paper investigates the effects and possible solutions to incomplete databases in regression and provides a systematic view of how missing data may affect regression results by analyzing actual publicly available databases. The results indicate that the impact of missing data can be significant, and the K-Nearest Neighbors method performs better in regression with missing data.
APPLIED ARTIFICIAL INTELLIGENCE
(2022)
Article
Green & Sustainable Science & Technology
Julian Bischof, Aidan Duffy
Summary: Existing NDB stock models predominantly focus on engineering models and building data, with most models not being complete life-cycle models and almost none including uncertainty analysis. The reproducibility of study results is poor, with a lack of representative input data present, limiting their usefulness for policymaking.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2022)
