Regularized Structural Equation Modeling to Detect Measurement Bias: Evaluation of Lasso, Adaptive Lasso, and Elastic Net
In: Structural equation modeling: a multidisciplinary journal, Band 27, Heft 5, S. 722-734
ISSN: 1532-8007
12 Ergebnisse
Sortierung:
In: Structural equation modeling: a multidisciplinary journal, Band 27, Heft 5, S. 722-734
ISSN: 1532-8007
In: Structural equation modeling: a multidisciplinary journal, Band 25, Heft 4, S. 639-649
ISSN: 1532-8007
In: Methodology in the social sciences
Cover -- Half Title Page -- Series Page -- Title Page -- Copyright -- Series Editor's Note -- Preface -- Contents -- Part I. Fundamental Concepts -- 1. Introduction -- 1.1 Why the Term Machine Learning? -- 1.1.1 Why Not Just Call It Statistics? -- 1.2 Why Do We Need Machine Learning? -- 1.2.1 Machine Learning Thesis -- 1.3 How Is This Book Different? -- 1.3.1 Prerequisites for the Book -- 1.4 Definitions -- 1.4.1 Model vs. Algorithm -- 1.4.2 Prediction -- 1.5 Software -- 1.6 Datasets -- 1.6.1 Grit -- 1.6.2 National Survey on Drug Use and Health from 2014 -- 1.6.3 Early Childhood Learning Study-Kindergarten Cohort -- 1.6.4 Big Five Inventory -- 1.6.5 Holzinger-Swineford -- 1.6.6 PHE Exposure -- 1.6.7 Professor Ratings -- 2. The Principles of Machine Learning Research -- 2.1 Key Terminology -- 2.2 Overview -- 2.3 Principle #1: Machine Learning Is Not Just Lazy Induction -- 2.3.1 Complexity -- 2.3.2 Abduction -- 2.4 Principle #2: Orienting Our Goals Relative to Prediction, Explanation, and Description -- 2.5 Principle #3: Labeling a Study as Exploratory or Confirmatory Is Too Simplistic -- 2.5.1 Model Size -- 2.5.2 Level of Hypothesis -- 2.5.3 Example -- 2.5.4 Types of Relationships -- 2.5.5 Exploratory Data Analysis -- 2.6 Principle #4: Report Everything -- 2.7 Summary -- 2.7.1 Further Reading -- 3. The Practices of Machine Learning -- 3.1 Key Terminology -- 3.2 Comparing Algorithms and Models -- 3.3 Model Fit -- 3.3.1 Regression -- 3.4 Bias-Variance Trade-Off -- 3.5 Resampling -- 3.5.1 k-Fold CV -- 3.5.2 Nested CV -- 3.5.3 Bootstrap Sampling -- 3.5.4 Recommendations -- 3.6 Classification -- 3.6.1 Receiver Operating Characteristic (ROC) Curves -- 3.7 Imbalanced Outcomes -- 3.7.1 Sampling -- 3.8 Conclusion -- 3.8.1 Further Reading -- 3.8.2 Computational Time and Resources -- Part II. Algorithms for Univariate Outcomes -- 4. Regularized Regression.
In: Methodology in the social sciences
"Over the past 20 years, there has been an incredible change in the size, structure, and types of data collected in the social and behavioral sciences. Thus, social and behavioral researchers have increasingly been asking the question: "What do I do with all of this data?" The goal of this book is to help answer that question. It is our viewpoint that in social and behavioral research, to answer the question "What do I do with all of this data?", one needs to know the latest advances in the algorithms and think deeply about the interplay of statistical algorithms, data, and theory. An important distinction between this book and most other books in the area of machine learning is our focus on theory"--
In: Structural equation modeling: a multidisciplinary journal, Band 26, Heft 6, S. 924-930
ISSN: 1532-8007
Methodological innovations have allowed researchers to consider increasingly sophisticated statistical models that are better in line with the complexities of real-world behavioral data. However, despite these powerful new analytic approaches, sample sizes may not always be sufficiently large to deal with the increase in model complexity. This difficult modeling scenario entails large models with a limited number of observations given the number of parameters. Here, we describe a particular strategy to overcome this challenge: regularization, a method of penalizing model complexity during estimation. Regularization has proven to be a viable option for estimating parameters in this small-sample, many-predictors setting, but so far it has been used mostly in linear regression models. We show how to integrate regularization within structural equation models, a popular analytic approach in psychology. We first describe the rationale behind regularization in regression contexts and how it can be extended to regularized structural equation modeling. We then evaluate our approach using a simulation study, showing that regularized structural equation modeling outperforms traditional structural equation modeling in situations with a large number of predictors and a small sample size. Next, we illustrate the power of this approach in two empirical examples: modeling the neural determinants of visual short-term memory and identifying demographic correlates of stress, anxiety, and depression. ; R. A. Kievit is supported by the Sir Henry Wellcome Trust (Grant 107392/Z/15/Z) and by an MRC Programme Grant (SUAG/014/RG91365). This project has also received funding from the European Union's Horizon 2020 Research and Innovation program (Grant 732592).
BASE
In: Crisis: the journal of crisis intervention and suicide prevention
ISSN: 2151-2396
Abstract: Background: The use of positive coping skills has demonstrated protective effects with regard to Nonsuicidal Self-Injury (NSSI) engagement; however, cross-sectional evidence suggests that the presence of comorbid conditions, such as alcohol use disorders, may negate these benefits. Aims: The current study leverages ecological momentary assessment (EMA) to examine the between-person and within-person relationships between positive coping strategies and NSSI risk among individuals with problematic alcohol use. Method: Undergraduate students ( n = 56) completed a 21-day EMA protocol, in which they completed four surveys per day asking about their use of several positive coping strategies and NSSI risk. Results: Socializing was the only coping strategy to demonstrate a protective effect on NSSI risk. Alternatively, the coping strategies of finding perspective, positive thinking, and sitting with feelings until they pass all increased risk for NSSI. Limitations: The current study was underpowered to disentangle relationships with urges to engage in NSSI and NSSI behaviors. Conclusion: The results suggest that using coping skills that may present physical barriers to engaging in NSSI may be effective for reducing momentary NSSI risk.
In: Structural equation modeling: a multidisciplinary journal, Band 24, Heft 2, S. 270-282
ISSN: 1532-8007
In: Structural equation modeling: a multidisciplinary journal, Band 23, Heft 4, S. 555-566
ISSN: 1532-8007
In: Structural equation modeling: a multidisciplinary journal, Band 25, Heft 1, S. 160-165
ISSN: 1532-8007
In: Structural equation modeling: a multidisciplinary journal, Band 24, Heft 5, S. 733-744
ISSN: 1532-8007
In: Structural equation modeling: a multidisciplinary journal, Band 28, Heft 1, S. 127-137
ISSN: 1532-8007