Article
Mathematics, Interdisciplinary Applications
Siwei Liu, Di Jody Zhou
Summary: Vector autoregressive (VAR) modelling is widely used in psychology for time series analysis. However, short time series in psychological studies can lead to overfitting and impair predictive ability. This simulation study found that cross-validation methods, especially blocked CV, are effective in estimating prediction errors and outperform traditional methods like AIC and BIC. CV methods tend to underestimate prediction errors of simpler models, but overestimate prediction errors of VAR models, especially with small sample sizes.
BRITISH JOURNAL OF MATHEMATICAL & STATISTICAL PSYCHOLOGY
(2023)
Article
Statistics & Probability
Jonas Krampe, Jens-Peter Kreiss, Efstathios Paparoditis
Summary: This paper focuses on sparse vector autoregressive models and develops bootstrap methods to infer properties of such processes. The methodology involves generating pseudo time series using an estimated version of the underlying model, and inference is conducted using de-sparsified estimators of the autoregressive model parameters. The theoretical results are supported by simulations and a real-life data application is presented.
Article
Engineering, Environmental
Babak Mohammadi, Saeid Mehdizadeh, Farshad Ahmadi, Nguyen Thi Thuy Lien, Nguyen Thi Thuy Linh, Quoc Bao Pham
Summary: This study focused on developing hybrid time series models to estimate air temperature parameters more accurately, with statistical metrics used to evaluate model performance. The results showed that the hybrid models outperformed the single models, and the combination of MLP and AR-ARCH models can provide more accurate temperature estimations. Additionally, temperature data from nearby stations can be utilized to predict the temperatures at desired locations.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2021)
Article
Economics
Kai Yang, Luan Zhao, Qian Hu, Wenshan Wang
Summary: This paper investigates the Bayesian quantile regression for capturing the conditional correlations between bivariate financial responses at different quantile levels in vector autoregressive models. A new Gibbs sampling algorithm is developed by introducing latent variables to draw posterior samples for the parameters and latent variables. Numerical simulations show that the algorithm converges fast and the Bayesian quantile estimators perform well.
COMPUTATIONAL ECONOMICS
(2023)
Review
Environmental Sciences
Jatinder Kaur, Kulwinder Singh Parmar, Sarbjit Singh
Summary: Globalization, industrialization, and urbanization have resulted in economic growth but have negatively impacted the environment. Understanding the detrimental effects on the environment and human health and implementing control measures is crucial. Time series analysis, particularly using the ARIMA model, can help in this direction due to its precision and flexibility. This study reviews the evolution of ARIMA and its applications in various fields, with a special focus on the environment, health, and air quality. It concludes that combined models or hybrid modeling with ARIMA are more robust and effective in capturing patterns in the series uniformly.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Computer Science, Artificial Intelligence
Zahra Hajirahimi, Mehdi Khashei
Summary: The paper discusses the importance of hybrid models in time series forecasting, highlighting the limitations of existing series hybrid models and introducing a parallel hybridization scheme to improve forecasting accuracy.
Article
Economics
Rong Chen, Han Xiao, Dan Yang
Summary: This paper discusses the use of matrix autoregressive models for analyzing observation data in a matrix form over time, proposing a novel approach that maintains matrix structure for dimensional reduction and interpretability enhancements. Probabilistic properties and estimation procedures of the models are investigated and demonstrated through simulated and real examples.
JOURNAL OF ECONOMETRICS
(2021)
Article
Physics, Multidisciplinary
Zahra Hajirahimi, Mehdi Khashei
Summary: This study proposes a hybrid model named SHOP, which integrates a parallel hybrid model using a series hybridization approach, to improve forecasting accuracy and overcome the drawbacks of parallel models.
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
(2022)
Article
Economics
Malte Lehna, Fabian Scheller, Helmut Herwartz
Summary: The variability of the day-ahead electricity spot price has increased due to the significant increase in renewable energies in electricity production. In this study, four different approaches, including (S)ARIMA(X), LSTM, CNN-LSTM, and VAR models, were compared for forecasting the German day-ahead electricity spot price. The LSTM model achieved the best overall forecasting performance, while the two-stage VAR model performed well for shorter prediction horizons. Moreover, combining both methods resulted in improved electricity spot price forecasts.
Article
Energy & Fuels
Faheem Jan, Ismail Shah, Sajid Ali
Summary: This study proposes a functional forecasting method for accurately predicting electricity prices. The method uses a functional autoregressive model for short-term price forecasting in the electricity markets and selects model dimensionality and lag structure through the use of functional final prediction error. A case study on the Italian electricity market shows that the proposed method performs relatively better than nonfunctional forecasting techniques.
Article
Economics
Jun Liao, Guohua Zou, Yan Gao, Xinyu Zhang
Summary: The paper introduces a new generalized Mallows model averaging criterion (GMMA) for choosing weights, suitable for candidate models with large dimensions. The research shows that the GMMA method has asymptotically optimal performance in prediction, solving Hansen's conjecture, and also derives the convergence rate of the optimal weight vector.
JOURNAL OF ECONOMETRICS
(2021)
Article
Computer Science, Artificial Intelligence
Zahra Hajirahimi, Mehdi Khashei
Summary: This paper investigates the problem of choosing the appropriate sequence of individual models in constructing series hybrid models for time series forecasting. By evaluating the performance of the linear-nonlinear and nonlinear-linear sequence modeling procedures, the study finds that choosing the nonlinear intelligent model as the first component leads to more accurate results.
NEURAL PROCESSING LETTERS
(2022)
Article
Computer Science, Interdisciplinary Applications
Mohammed Bouchouia, Francois Portier
Summary: A statistical predictive model is used to model road traffic by regenerating a high-dimensional time-series at the end of each day. Prediction is based on daily modeling using a vector autoregressive model with l(1)-penalization of regression coefficients. The approach, compared to state-of-the-art methods including neural networks, is highly competitive in terms of prediction and enables the identification of the most determinant sections of the road network.
COMPUTATIONAL STATISTICS & DATA ANALYSIS
(2021)
Article
Environmental Studies
Ryan P. Thombs, Xiaorui Huang, Andrew K. Jorgenson
Summary: This study focuses on the interrelationships among economic development, energy systems, and the environment by using semiparametric, time-varying vector autoregressive models to analyze data from the United States, illustrating how the relationships between different indicators have changed over time.
ENERGY RESEARCH & SOCIAL SCIENCE
(2021)
Article
Psychology, Multidisciplinary
Jose Antonio Cecchini-Estrada, Javier Fernandez-Rio, Daniel Fernandez-Arguelles
Summary: Using autoregressive models, this study concludes that there are bidirectional relationships between physical activity and sleep. The sleep variables of sleep onset, sleep offset, and sedentary behavior are influenced by autoregressive effects, while moderate-to-vigorous physical activity is not related to any of the sleep variables.
Article
Psychology, Clinical
Kenneth S. Kendler, Judith G. M. Rosmalen, Henrik Ohlsson, Jan Sundquist, Kristina Sundquist
Summary: By examining the genetic risk patterns, this study clarifies the etiology of functional somatic disorders (FSD). Patients with fibromyalgia (FM) have elevated genetic risk for various disorders including pain syndromes, internalizing disorders, autoimmune disorders, and sleep disorders. In contrast, major depression (MD) and rheumatoid arthritis (RA) have more restricted genetic risk profiles. This study suggests that FSD arise from a distinctive pattern of genetic liability for a diversity of psychiatric, autoimmune, pain, sleep, and functional somatic disorders.
PSYCHOLOGICAL MEDICINE
(2023)
Editorial Material
Psychology, Developmental
Annelieke M. Roest, Ymkje Anna de Vries, Albert W. Wienen, Peter de Jonge
Summary: Mental disorders starting in childhood can have severe consequences throughout an individual's lifespan. While effective short-term treatments exist for common mental disorders in young people, little is known about their long-term effects. This editorial perspective examines the long-term effectiveness and safety of treatments for attention deficit hyperactivity disorder, behavior disorders, and anxiety and depressive disorders in children aged 6 to 12 years, and discusses methodological difficulties and risk-benefit ratio of these treatments.
JOURNAL OF CHILD PSYCHOLOGY AND PSYCHIATRY
(2023)
Article
Psychology, Experimental
Anne M. Reitsema, Bertus F. Jeronimus, Elisabeth H. Bos, Peter de Jonge, Pontus Leander
Summary: This study examined the hedonic adaptation trajectories of positive and negative affect in different age groups during the first wave of the COVID-19 pandemic. The results showed that these trajectories were largely similar across age groups, suggesting that age differences in emotional well-being are limited to mean-level differences rather than emotion dynamics. However, there were substantial individual differences in emotional adaptation. The emotional recovery trajectories were virtually similar across age groups, valence, and arousal levels in 33 countries.
Review
Psychiatry
Nick Mamo, Manouk Van de Klundert, Lineke Tak, Tim Olde Hartman, Denise Hanssen, Judith Rosmalen
Summary: Functional disorders (FD) are complex conditions that often require multidisciplinary involvement. Collaborative care networks (CCN) can harness the potential of a multidisciplinary team (MDT) in FD care. A systematic review of existing CCNs in FD revealed heterogeneity in their structures and processes, highlighting the need for better evaluation, collaboration, and education processes.
JOURNAL OF PSYCHOSOMATIC RESEARCH
(2023)
Article
Psychiatry
Iris Jonker, Sjoerd Visschedijk, Judith G. M. Rosmalen, Hendrika Maria Schenk, Sonja L. Van Ockenburg
Summary: The study examined the complex relationships between sleep, inflammatory markers, and somatic symptoms, and found individual differences in these associations. Analysis of data from 10 healthy individuals over a period of 63 days revealed varying and sometimes contradictory associations between sleep, inflammatory markers, and somatic symptoms.
PSYCHOSOMATIC MEDICINE
(2023)
Article
Health Care Sciences & Services
Aranka V. V. Ballering, Tim C. Olde C. Hartman, Robert Verheij, Judith G. M. Rosmalen
Summary: Women are more likely than men to consult general practitioners, and factors related to help-seeking behavior may be associated with sex rather than gender. However, gender-related variables, such as working days, may also be associated with help-seeking behavior.
SCANDINAVIAN JOURNAL OF PRIMARY HEALTH CARE
(2023)
Article
Oncology
Lonneke A. van Tuijl, Maartje Basten, Kuan-Yu Pan, Roel Vermeulen, Luetzen Portengen, Alexander de Graeff, Joost Dekker, Mirjam I. Geerlings, Adriaan Hoogendoorn, Femke Lamers, Adri C. Voogd, Jessica Abell, Philip Awadalla, Aartjan T. F. Beekman, Ottar Bjerkeset, Andy Boyd, Yunsong Cui, Philipp Frank, Henrike Galenkamp, Bert Garssen, Sean Hellingman, Martijn Huisman, Anke Huss, Trynke R. de Jong, Melanie R. Keats, Almar A. L. Kok, Steinar Krokstad, Flora E. van Leeuwen, Annemarie I. Luik, Nolwenn Noisel, N. Charlotte Onland-Moret, Yves Payette, Brenda W. J. H. Penninx, Ina Rissanen, Annelieke M. Roest, Rikje Ruiter, Robert A. Schoevers, David Soave, Mandy Spaan, Andrew Steptoe, Karien Stronks, Erik R. Sund, Ellen Sweeney, Emma L. Twait, Alison Teyhan, W. M. Monique Verschuren, Kimberly D. van der Willik, Judith G. M. Rosmalen, Adelita V. Ranchor
Summary: A meta-analysis of individual participant data from 18 cohorts found no associations between depression or anxiety and most types of cancer, except for lung cancer and smoking-related cancers. The associations with lung and smoking-related cancers were attenuated when adjusting for known risk factors.
Article
Public, Environmental & Occupational Health
Sander K. R. van Zon, Aranka Ballering, Sandra Brouwer, Judith G. M. Rosmalen, Lifelines Corona Res Initiative
Summary: To improve research and care for patients with post-COVID-19 condition, it is important to understand the different subtypes of the condition and their risk factors. This study used data from a large cohort to identify risk factors for post-COVID-19 condition and specific symptom profiles. The findings suggest that SARS-CoV-2 may trigger different pathophysiological mechanisms leading to different subtypes of post-COVID-19 condition.
EUROPEAN JOURNAL OF PUBLIC HEALTH
(2023)
Editorial Material
Psychology, Developmental
Annelieke M. Roest, Ymkje Anna de Vries, Albert W. Wienen, Peter de Jonge
Summary: In their response, Dekkers et al. argue that treatment is the best option for children with mental disorders due to 'sound evidence' of its effectiveness in both short and long-term. While we agree that there is evidence for short-term effectiveness and certain treatments have shown some long-term effects, such as behavioral parent training for behavioral disorders, we strongly disagree that there is solid evidence for long-term effectiveness overall.
JOURNAL OF CHILD PSYCHOLOGY AND PSYCHIATRY
(2023)
Review
Psychology, Social
Jannis Kreienkamp, Laura F. Bringmann, Raili F. Engler, Peter de Jonge, Kai Epstude
Summary: One of the key challenges in researching psychological acculturation is the diversity in theories and measures, which makes it difficult to compare past literature and hinder theoretical integration. To address this, the authors propose utilizing the four basic aspects of human experiences (wanting, feeling, thinking, and doing) as a conceptual framework. They use this framework to assess past theoretical, psychometric, and empirical literature, finding that it allows for examination and comparison of past conceptualizations and provides novel insights for future research and interventions.
PERSONALITY AND SOCIAL PSYCHOLOGY REVIEW
(2023)
Article
Psychology, Multidisciplinary
Anne M. van Valkengoed, Linda Steg, Peter de Jonge
Summary: Climate anxiety refers to persistent, difficult-to-control apprehensiveness and worry about climate change. Emotion researchers can contribute by better understanding its prevalence, indicators, causes, and consequences. They can provide integrative and functional theories, explain the reasons behind climate anxiety, theorize how it motivates climate action, and develop coping strategies based on emotion regulation theory.
Article
Multidisciplinary Sciences
Yvonne M. J. H. Goertz, Martijn Spruit, Maarten Van Herck, Nicole Dukers-Muijrers, Carla J. H. van der Kallen, Chris Burtin, Daisy J. A. Janssen, Lifelines Corona Res Initiative
Summary: This study evaluates the presence of symptoms before, during, and after a positive SARS-CoV-2 PCR test and compares the symptom burden with those who tested negative. Participants from the Dutch Lifelines COVID-19 Cohort Study were surveyed about demographics, COVID-19 diagnosis, severity, QoL, and symptoms. The results show that most symptoms were more common after a positive test compared to before (p < 0.05), except fever. Symptoms were also common in those who tested negative. Quality of life decreased around the test for both positive and negative individuals, with a greater deterioration for positives.
SCIENTIFIC REPORTS
(2023)
Article
Psychiatry
Maruschka N. Sluiter, Elisabeth H. Bos, Jeannette M. Doornenbal, Peter de Jonge, Laura Batstra
Summary: This preliminary study investigated the effect of a group parent training program without child-bound classifications on children with attention-deficit/hyperactivity disorder. The results showed that the intervention group had significantly lower scores on parental stress and communication problems compared with the control group. However, there were no significant differences in attention and hyperactivity problems, oppositional defiant problems, and responsivity.
JOURNAL OF PSYCHIATRIC PRACTICE
(2023)
Article
Psychology, Social
Jannis Kreienkamp, Maximilian Agostini, Laura F. Bringmann, Peter de Jonge, Kai Epstude
Summary: This article presents evidence that the fulfillment of situational needs during real-life intergroup contacts significantly predicts perceived interaction quality and positive outgroup attitudes. Methodologically, it supports the emerging practice of capturing real-life interactions using intensive longitudinal data. Theoretically, it highlights motivational fulfillment as a flexible and effective mechanism for understanding positive intergroup contact.
PERSONALITY AND SOCIAL PSYCHOLOGY BULLETIN
(2023)