Review
Psychology, Multidisciplinary
Andreas Gegenfurtner
Summary: This meta-analytic review aimed to estimate the differences in model fit between bifactor exploratory structural equation modeling (B-ESEM) and other models. By analyzing 158 studies, it was found that B-ESEM model fit was superior to reference models. The results also indicated that model fit is sensitive to sample size, item number, and the number of specific and general factors in a model.
FRONTIERS IN PSYCHOLOGY
(2022)
Article
Psychology, Mathematical
Suzanne Jak, Terrence D. Jorgensen, Mathilde G. E. Verdam, Frans J. Oort, Louise Elffers
Summary: This tutorial explains how to conduct power calculations for SEM using power4SEM without using Monte Carlo methods. By focusing on model fit instead of statistical significance, power4SEM provides two computationally efficient methods for power calculations of SEM.
BEHAVIOR RESEARCH METHODS
(2021)
Article
Psychology, Multidisciplinary
Bryant M. Stone
Summary: The paper discusses the role of fit indices in evaluating the fit of structural equation models and potential misuse by researchers. The author highlights two ethical dilemmas that may arise when using fit indices and provides solutions to reduce questionable research practices.
FRONTIERS IN PSYCHOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Gary F. Templeton, Martin Kang, Nargess Tahmasbi
Summary: This study introduces a single imputation method to address missing input values in data, improving statistical power and emulation compared to other popular multiple imputation methods. It also presents new imputation performance metrics and visualizations, as well as specified imputation models for commonly used inputs to firm performance calculations.
DECISION SUPPORT SYSTEMS
(2021)
Article
Business, Finance
Michael Michaelides
Summary: The majority of empirical studies in finance use large sample sizes and conventional thresholds for statistical significance, potentially leading to spurious results. This paper introduces a rule of thumb for determining appropriate thresholds for statistical significance and suggests that the list of statistically significant findings in finance literature may shrink significantly after accounting for large sample size bias.
FINANCE RESEARCH LETTERS
(2021)
Article
Multidisciplinary Sciences
Amrit Sudershan, Kanak Mahajan, Rakesh K. Panjaliya, Manoj K. Dhar, Parvinder Kumar
Summary: Sampling methods for studying population behavior are uncertain and require representative samples for generalization. Sample size greatly affects the detection of research effects, with smaller samples having lower statistical power and higher risk of missing underlying differences. This study provides a calculation method for determining sample availability during research.
SCIENTIFIC REPORTS
(2022)
Article
Psychology, Multidisciplinary
Daniel H. Baker, Greta Vilidaite, Freya A. Lygo, Anika K. Smith, Tessa R. Flack, Andre D. Gouws, Timothy J. Andrews
Summary: When designing experimental studies, determining the number of trials and participants is crucial for statistical power. Research shows that the number of trials can have a significant impact on statistical power, especially when within-participant variance is large compared to between-participants variance.
PSYCHOLOGICAL METHODS
(2021)
Article
Health Care Sciences & Services
Samantha F. Anderson
Summary: This article addresses common misconceptions in sample size planning in the field of HRQOL, providing accessible corrections and demonstrating the benefits of a nuanced understanding of sample size planning for researchers.
QUALITY OF LIFE RESEARCH
(2022)
Article
Mathematics, Interdisciplinary Applications
Victoria Savalei
Summary: Current computations of fit indices in structural equation modeling indicate that categorical data may lead to accepting poorly fitting models more frequently than continuous data. The article explains this issue and proposes alternative ways to compute fit indices with categorical data, showing that the new methods better match values with continuous data and perform well across various conditions.
MULTIVARIATE BEHAVIORAL RESEARCH
(2021)
Article
Ecology
Beth E. Ross, Mitch D. Weegman
Summary: Understanding mechanistic causes of population change is critical for managing and conserving species. Integrated population models (IPMs) allow for quantifying population changes while directly relating environmental drivers to vital rates. The study found that the temporal duration of a study and effect size had the greatest influence on the power to identify trends in adult survival and fecundity. IPMs had greater power to identify trends and environmental effects on vital rates compared to traditional analysis methods.
ECOLOGICAL APPLICATIONS
(2022)
Review
Psychology, Clinical
Raphael Schuster, Tim Kaiser, Yannik Terhorst, Eva Maria Messner, Lucia-Maria Strohmeier, Anton-Rupert Laireiter
Summary: The study found that researchers typically achieve their determined sample size goals and pre-registration rates are on the rise. Study context appears to be more important than study design during study planning. Digital psychiatry may help mitigate the challenge of underpowered studies.
PSYCHOLOGICAL MEDICINE
(2021)
Article
Computer Science, Interdisciplinary Applications
Dimitrios Bagkavos, Prakash N. Patil
Summary: A novel goodness-of-fit test is introduced to assess the validity of maximum likelihood estimates of normal mixture densities with known number of components. The authors provide theoretical quantification of the test statistic's size and power functions and derive a closed-form bandwidth rule and a cut-off point suitable for finite sample implementations. Extensive simulation study and analysis of real-world datasets demonstrate the superiority of this new test in all considered examples.
COMPUTATIONAL STATISTICS & DATA ANALYSIS
(2023)
Article
Neurosciences
Gang Chen, Daniel S. Pine, Melissa A. Brotman, Ashley R. Smith, Robert W. Cox, Paul A. Taylor, Simone P. Haller
Summary: Trials play a crucial role in task-based neuroimaging, impacting statistical efficiency and condition-level generalizability. Increasing both trial and subject sample sizes can improve statistical efficiency more effectively than focusing on subjects alone, and trial-level modeling may be necessary for accurately assessing effect estimates with small trial size.
Article
Engineering, Multidisciplinary
Yuwei Zhao, Zubair Ahmad, Amani Alrumayh, M. Yusuf, Ramy Aldallal, Assem Elshenawy, Fathy H. Riad
Summary: This paper introduces a new statistical methodology, called the logarithmic -U family of distributions, to update the flexibility level of traditional distributions. The parameters estimation of logarithmic -U distributions using maximum likelihood method is discussed, and some mathematical properties are derived. The logarithmic Weibull distribution, an updated version of the Weibull model, is introduced using the logarithmic -U method. A simulation study is provided for the logarithmic Weibull distribution. Practical illustrations of the logarithmic Weibull distribution are shown by analyzing two data sets from the engineering sector.
ALEXANDRIA ENGINEERING JOURNAL
(2023)
Article
Materials Science, Multidisciplinary
Bartosz Krajewski, Marcin Mierzejewski, Janez Bonca
Summary: This study investigates the sample-to-sample fluctuations of the gap ratio in the energy spectra of finite disordered spin chains. It is found that the fluctuations in the microscopic models significantly exceed those in the Rosenzweig-Porter (RP) model near the ergodic-nonergodic crossover. By introducing an extension to the RP model, the fluctuations in all regimes, including the ergodic and nonergodic regimes as well as the crossover between them, can be accurately reproduced. Furthermore, this study demonstrates methods to reduce the sample-to-sample fluctuations in both studied microscopic models.
Article
Mathematics, Interdisciplinary Applications
Lisa J. Jobst, Daniel W. Heck, Morten Moshagen
JOURNAL OF MATHEMATICAL PSYCHOLOGY
(2020)
Article
Psychology, Educational
Lisa J. Jobst, Max Auerswald, Morten Moshagen
Summary: A study was conducted to investigate the effects of non-normality in structural equation modeling by manipulating the multivariate distribution in a Monte Carlo simulation. Results showed that all measures of fit were influenced by the source of non-normality, but with varying patterns depending on the estimation methods used.
EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT
(2022)
Article
Mathematics, Interdisciplinary Applications
Lisa J. Jobst, Christoph Heine, Max Auerswald, Morten Moshagen
Summary: The study analyzed the impact of different corrections on the root mean square error of approximation in structural equation modeling, finding that corrected values exhibit a stronger bias in non-normality and the extent of bias is also influenced by properties of the multivariate distribution.
STRUCTURAL EQUATION MODELING-A MULTIDISCIPLINARY JOURNAL
(2021)
Article
Psychology, Clinical
Martina Bader, Johanna Hartung, Benjamin E. Hilbig, Ingo Zettler, Morten Moshagen, Oliver Wilhelm
Summary: This study examines the internal structure of the Dark Factor of Personality (D), finding that D consists of five specific factors - Callousness, Deceitfulness, Narcissistic Entitlement, Sadism, and Vindictiveness - which best describe the internal structure of D and its relation to aversive traits.
PSYCHOLOGICAL ASSESSMENT
(2021)
Article
Psychology, Clinical
Martina Bader, Luisa K. Horsten, Benjamin E. Hilbig, Ingo Zettler, Morten Moshagen
Summary: This study comprehensively evaluated the German version of D70 and its shorter versions, confirming their reliability and validity for psychometric assessment, with moderate self-other agreement.
JOURNAL OF PERSONALITY ASSESSMENT
(2022)
Article
Mathematics, Interdisciplinary Applications
Martina Bader, Lisa J. Jobst, Morten Moshagen
Summary: Despite the application of bifactor models, little research has considered sample sizes required for this type of model. In this study, we illustrate how to determine sample size requirements for bifactor models using Monte Carlo simulations in R. Results show that a sample size of 500 is often sufficient, but exact requirements depend on various model characteristics.
STRUCTURAL EQUATION MODELING-A MULTIDISCIPLINARY JOURNAL
(2022)
Article
Psychology, Multidisciplinary
Martina Bader, Morten Moshagen
Summary: Model selection is a common issue in structural equation modeling (SEM), and a trade-off between goodness-of-fit and model parsimony is often sought. This investigation assessed the fitting propensity of frequently used SEM models and evaluated the performance of fit indices and information criteria in controlling for fitting propensity. The results showed that differences in fitting propensity were mostly driven by the number of free parameters, and fit indices adjusting for the number of parameters adequately accounted for these differences.
PSYCHOLOGICAL METHODS
(2022)
Article
Psychology, Social
Martina Bader, Benjamin E. Hilbig, Ingo Zettler, Morten Moshagen
Summary: This study proposes a new theoretical view that conceptualizes the Dark Triad traits as specific manifestations of the common core of aversive traits, flavored by unique, essentially non-aversive characteristics. The empirical findings from two studies support this view and reveal a discrepancy between the current conceptualization and empirical structure of the Dark Triad traits.
JOURNAL OF PERSONALITY
(2023)
Article
Psychology, Clinical
Martina Bader, Lisa J. Jobst, Ingo Zettler, Benjamin E. Hilbig, Morten Moshagen
Summary: Comparability of measurement across different cultural groups is crucial for cross-cultural assessment, but achieving cross-cultural measurement invariance can be challenging. Noninvariance in measurement may stem from translation bias, culture bias, or comprehension bias, depending on the language version used. The Culture, Comprehension, and Translation Bias (CCT) procedure outlines a method to distinguish these sources of item noninvariance and improve the accuracy of cross-cultural assessment through multiple pairwise comparisons.
PSYCHOLOGICAL ASSESSMENT
(2021)