1
|
Sigrist C, Ottaviani C, Baumeister-Lingens L, Bussone S, Pesca C, Kaess M, Carola V, Koenig J. A sex-specific pathway linking early life maltreatment, vagal activity, and depressive symptoms. Eur J Psychotraumatol 2024; 15:2325247. [PMID: 38512074 PMCID: PMC10962311 DOI: 10.1080/20008066.2024.2325247] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/10/2023] [Accepted: 12/08/2023] [Indexed: 03/22/2024] Open
Abstract
Background: Experiences of early life maltreatment (ELM) are alarmingly common and represent a risk factor for the development of psychopathology, particularly depression. Research has focused on alterations in autonomic nervous system (ANS) functioning as a mediator of negative mental health outcomes associated with ELM. Early alterations in autonomic vagal activity (vmHRV) may moderate the relationship between ELM and depression, particularly when considering forms of emotional maltreatment. Recent evidence suggests that the relationships of both ELM and vmHRV with depression may be non-linear, particularly considering females.Objective: Building on and extending theoretical considerations and previous work, the present work aims to further the current understanding of the complex relationships between ELM exposure, vmHRV, and depression.Methods: This study uses an adaptive modelling approach, combining exploratory network-based analyses with linear and quadratic moderation analyses, drawing on a large sample of males and females across adolescence (total N = 213; outpatient at-risk sample and healthy controls) and adulthood (total N = 85; community-based convenience sample).Results: Exploratory network-based analyses reveal that exposure to emotional abuse is particularly central within a network of ELM subtypes, depressive symptoms, and concurrent vmHRV in both adolescents and adults. In adults, emotional neglect shows strong associations with both emotional abuse and vmHRV and is highly central as a network node, which is not observed in adolescents. Moderator analyses reveal significant interactions between emotional maltreatment and vmHRV predicting depressive symptoms in adult females. Significant quadratic relationships of emotional maltreatment and vmHRV with depression are observed in both adolescent and adult females.Conclusions: The present findings contribute to the understanding of the psychological and physiological mechanisms by which ELM acts as a risk factor for the development of depression. Ultimately, this will contribute to the development of targeted and effective intervention strategies to mitigate the detrimental effects of early adversity.
Collapse
Affiliation(s)
- Christine Sigrist
- University of Cologne, Faculty of Medicine and University Hospital Cologne, Department of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, Cologne, Germany
| | - Cristina Ottaviani
- Department of Psychology, Faculty of Medicine and Psychology, Sapienza University of Rome, Rome, Italy
- IRCCS Santa Lucia Foundation, Rome, Italy
| | - Luise Baumeister-Lingens
- University of Cologne, Faculty of Medicine and University Hospital Cologne, Department of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, Cologne, Germany
| | - Silvia Bussone
- Department of Dynamic and Clinical Psychology and Health Studies, “Sapienza” University of Rome, Rome, Italy
| | - Chiara Pesca
- Department of Dynamic and Clinical Psychology and Health Studies, “Sapienza” University of Rome, Rome, Italy
| | - Michael Kaess
- Department of Child and Adolescent Psychiatry, Centre for Psychosocial Medicine, Heidelberg University, Heidelberg, Germany
- University Hospital of Child and Adolescent Psychiatry and Psychotherapy, University of Bern, Bern, Switzerland
| | - Valeria Carola
- IRCCS Santa Lucia Foundation, Rome, Italy
- Department of Dynamic and Clinical Psychology and Health Studies, “Sapienza” University of Rome, Rome, Italy
| | - Julian Koenig
- University of Cologne, Faculty of Medicine and University Hospital Cologne, Department of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, Cologne, Germany
- Department of Child and Adolescent Psychiatry, Centre for Psychosocial Medicine, Heidelberg University, Heidelberg, Germany
| |
Collapse
|
2
|
Brusco M, Steinley D, Watts AL. Improving the Walktrap Algorithm Using K-Means Clustering. MULTIVARIATE BEHAVIORAL RESEARCH 2024; 59:266-288. [PMID: 38361218 PMCID: PMC11014777 DOI: 10.1080/00273171.2023.2254767] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/17/2024]
Abstract
The walktrap algorithm is one of the most popular community-detection methods in psychological research. Several simulation studies have shown that it is often effective at determining the correct number of communities and assigning items to their proper community. Nevertheless, it is important to recognize that the walktrap algorithm relies on hierarchical clustering because it was originally developed for networks much larger than those encountered in psychological research. In this paper, we present and demonstrate a computational alternative to the hierarchical algorithm that is conceptually easier to understand. More importantly, we show that better solutions to the sum-of-squares optimization problem that is heuristically tackled by hierarchical clustering in the walktrap algorithm can often be obtained using exact or approximate methods for K-means clustering. Three simulation studies and analyses of empirical networks were completed to assess the impact of better sum-of-squares solutions.
Collapse
|
3
|
Calugi S, Segattini B, Cattaneo G, Chimini M, Dalle Grave A, Dametti L, Molgora M, Dalle Grave R. Weight Bias Internalization and Eating Disorder Psychopathology in Treatment-Seeking Patients with Obesity. Nutrients 2023; 15:2932. [PMID: 37447258 DOI: 10.3390/nu15132932] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2023] [Revised: 06/23/2023] [Accepted: 06/26/2023] [Indexed: 07/15/2023] Open
Abstract
This study aimed to investigate the relationship between weight bias internalization and eating disorder psychopathology in treatment-seeking patients with severe obesity using a network approach. Two thousand one hundred and thirteen patients with obesity were consecutively admitted to a specialist clinical unit for obesity and were recruited from January 2016 to February 2023. Body mass index was measured, and each patient completed the Weight Bias Internalization Scale (WBSI) and the Eating Disorder Examination Interview (EDE). Network analysis showed that the most central and highly interconnected nodes in the network were related to the EDE items exposure avoidance, dissatisfaction with shape, and wanting an empty stomach. Bridge nodes were found, but the bootstrap difference test on expected bridge influence indicated non-significant centrality differences. Nevertheless, the eating disorder psychopathology and weight bias internalization network structure in patients seeking treatment for obesity indicate the prominent roles of body dissatisfaction and control of eating and weight in these psychological constructs. This finding, if replicated, could pave the way for a new understanding of the psychological mechanisms operating in patients with obesity.
Collapse
Affiliation(s)
- Simona Calugi
- Department of Eating and Weight Disorders, Villa Garda Hospital, Via Monte Baldo 89, 37016 Garda, VR, Italy
| | - Barbara Segattini
- Department of Eating and Weight Disorders, Villa Garda Hospital, Via Monte Baldo 89, 37016 Garda, VR, Italy
| | - Gianmatteo Cattaneo
- Department of Eating and Weight Disorders, Villa Garda Hospital, Via Monte Baldo 89, 37016 Garda, VR, Italy
| | - Mirko Chimini
- Department of Eating and Weight Disorders, Villa Garda Hospital, Via Monte Baldo 89, 37016 Garda, VR, Italy
| | - Anna Dalle Grave
- Department of Eating and Weight Disorders, Villa Garda Hospital, Via Monte Baldo 89, 37016 Garda, VR, Italy
| | - Laura Dametti
- Department of Eating and Weight Disorders, Villa Garda Hospital, Via Monte Baldo 89, 37016 Garda, VR, Italy
| | - Manuela Molgora
- Department of Eating and Weight Disorders, Villa Garda Hospital, Via Monte Baldo 89, 37016 Garda, VR, Italy
| | - Riccardo Dalle Grave
- Department of Eating and Weight Disorders, Villa Garda Hospital, Via Monte Baldo 89, 37016 Garda, VR, Italy
| |
Collapse
|
4
|
Wang S, Zhao S, Guo Y, Huang C, Zhang P, She L, Xiang B, Zeng J, Zhou F, Xie X, Yang M. A network analysis of subjective well-being in Chinese high school students. BMC Public Health 2023; 23:1249. [PMID: 37370106 DOI: 10.1186/s12889-023-16156-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/04/2023] [Accepted: 06/20/2023] [Indexed: 06/29/2023] Open
Abstract
BACKGROUND The psychological situation of high school students during adolescence is not promising, and the most obvious manifestation is the lack of subjective well-being (SWB). This network analysis presents a model of the interaction and correlation between different items of SWB, identifying the most central items for high school students. METHODS Through offline and online surveys, 4,378 questionnaires were sent out and finally 4,282 Chinese high school students were available. The response rate was 97.807%. The study used the eLASSO method to estimate the network structure and centrality measures. This algorithm used the EBIC to select the best neighbor factor for each node. RESULTS The average age for high school students was 16.320 years old and the average SWB score was 76.680. The distribution of SWB between male and female students was significant different (P < 0.001). S8 (Have you been anxious, worried, or upset) was the node with the highest strength and expected influence. The network structure and centrality remained stable after discarding 75% of the sample at random. Except for S15 (How concerned or worried about your health have you been), all nodes were positively correlated with each other (P < 0.01). The network structure of SWB was similar for female and male students (network strength: 8.482 for male participants; 8.323 for female participants; P = 0.159), as well as for rural and urban students (network strength: 8.500 for rural students; 8.315 for urban students; P = 0.140). CONCLUSION Targeting S8 (Have you been anxious, worried, or upset) as a potential intervention target may increase high school students' SWB effectively.
Collapse
Affiliation(s)
- Shiwei Wang
- Research Center for Health Promotion in Women, Youth and Children, School of public health, Wuhan University of science and technology, Wuhan, 430065, Hubei Province, China
| | - Siqi Zhao
- Wuhan centers for disease control and prevention, Wuhan, 430022, Hubei Province, China
| | - Yan Guo
- Wuhan centers for disease control and prevention, Wuhan, 430022, Hubei Province, China
| | - Chengjing Huang
- Research Center for Health Promotion in Women, Youth and Children, School of public health, Wuhan University of science and technology, Wuhan, 430065, Hubei Province, China
| | - Pei Zhang
- Research Center for Health Promotion in Women, Youth and Children, School of public health, Wuhan University of science and technology, Wuhan, 430065, Hubei Province, China
| | - Lu She
- Research Center for Health Promotion in Women, Youth and Children, School of public health, Wuhan University of science and technology, Wuhan, 430065, Hubei Province, China
| | - Bing Xiang
- Research Center for Health Promotion in Women, Youth and Children, School of public health, Wuhan University of science and technology, Wuhan, 430065, Hubei Province, China
| | - Jing Zeng
- Research Center for Health Promotion in Women, Youth and Children, School of public health, Wuhan University of science and technology, Wuhan, 430065, Hubei Province, China
| | - Feng Zhou
- Research Center for Health Promotion in Women, Youth and Children, School of public health, Wuhan University of science and technology, Wuhan, 430065, Hubei Province, China
| | - Xinyan Xie
- Research Center for Health Promotion in Women, Youth and Children, School of public health, Wuhan University of science and technology, Wuhan, 430065, Hubei Province, China
| | - Mei Yang
- Research Center for Health Promotion in Women, Youth and Children, School of public health, Wuhan University of science and technology, Wuhan, 430065, Hubei Province, China.
| |
Collapse
|
5
|
Blondino CT, Prom-Wormley EC. A network approach to substance use, internalizing, and externalizing comorbidity in U.S. adults. Addict Behav 2022; 134:107421. [PMID: 35878503 DOI: 10.1016/j.addbeh.2022.107421] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2020] [Revised: 04/11/2022] [Accepted: 07/01/2022] [Indexed: 11/24/2022]
Abstract
INTRODUCTION Use of conventional cigarettes (CIG), alcohol, marijuana, and sedatives [i.e., benzodiazepines and barbiturates]) commonly co-occur with internalizing and externalizing disorders. It is unclear how these relationships extend to electronic cigarettes (ECIGs) and prescription drugs not prescribed (i.e., sedatives, tranquilizers, and painkillers [PDNP]), and whether they differ by gender. METHODS Adult data (N = 30,211) from Wave 1 (2013-2014) of the Population Assessment of Tobacco and Health Study were used to estimate a network of current or past-month use for six substances, experiencing four internalizing symptoms in the past month, and experiencing seven externalizing symptoms in the past month. Visual comparisons, global strength invariance, network structure invariance, and edge strength invariance were tested to detail substance use and internalizing/externalizing symptom networks. RESULTS Overall, networks were consistent between men and women. The strongest substance use/mental health symptom connections estimated as edge-weights (EW) were between marijuana with lying (EW = 0.60, 95% CI = 0.49; 0.70), marijuana with engaging in fights (EW = 0.54, 95% CI = 0.27; 0.81), PDNP with having trouble sleeping (EW = 0.53, 95% CI = 0.40; 0.66), and alcohol and impulsivity (EW = 0.48, 95% CI = 0.42; 0.53). DISCUSSION There were many weak connections throughout the substance use and internalizing/externalizing network. A few important connections were identified and encourage future study. In particular, PDNP was most strongly associated with internalizing symptoms. Marijuana, alcohol and PDNP use were most strongly associated with externalizing symptoms.
Collapse
Affiliation(s)
- Courtney T Blondino
- Division of Epidemiology, Department of Family Medicine and Population Health, Virginia Commonwealth University School of Medicine, 830 East Main Street, PO Box 980212, Richmond, VA 23298-0212, USA.
| | - Elizabeth C Prom-Wormley
- Division of Epidemiology, Department of Family Medicine and Population Health, Virginia Commonwealth University School of Medicine, 830 East Main Street, PO Box 980212, Richmond, VA 23298-0212, USA.
| |
Collapse
|
6
|
Calugi S, Dametti L, Dalle Grave A, Dalle Grave R. Changes in specific and nonspecific psychopathology network structure after intensive cognitive behavior therapy in patients with anorexia nervosa. Int J Eat Disord 2022; 55:1090-1099. [PMID: 35689570 DOI: 10.1002/eat.23755] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/10/2022] [Revised: 05/23/2022] [Accepted: 05/23/2022] [Indexed: 12/19/2022]
Abstract
OBJECTIVE This study aimed to compare eating disorder-specific and nonspecific clinical features in patients with anorexia nervosa before and after intensive enhanced cognitive behavior therapy (CBT-E) via network analysis. METHODS All consecutive patients admitted to intensive CBT-E were eligible, and the sample comprised patients aged ≥16 years who completed a 20-week intensive CBT-E program. Body mass index (BMI), Eating Disorder Examination Questionnaire and Brief Symptoms Inventory responses were gathered at baseline and end of treatment, and used to generate statistical networks of the connections between symptoms (nodes) and the strength and centrality thereof. RESULTS A total of 214 patients were included. Most nodes had relatively similar centrality compared to other nodes in the networks. "Eating concern" and "phobic anxiety" showed the greatest bridge centrality at both time points. No differences were found between baseline and the end of treatment in either global network or individual connection strengths. CONCLUSION These findings suggest that some clinical expressions not specific to eating-disorder psychopathology remain strongly connected in the generalized network of patients with anorexia nervosa after CBT-E. Future research should examine whether additional procedures specifically designed to target these symptoms should be integrated into this and other treatments.
Collapse
Affiliation(s)
- Simona Calugi
- Department of Eating and Weight Disorders, Villa Garda Hospital, Garda, Italy
| | - Laura Dametti
- Department of Eating and Weight Disorders, Villa Garda Hospital, Garda, Italy
| | - Anna Dalle Grave
- Department of Eating and Weight Disorders, Villa Garda Hospital, Garda, Italy
| | | |
Collapse
|
7
|
Marsman M, Huth K, Waldorp LJ, Ntzoufras I. Objective Bayesian Edge Screening and Structure Selection for Ising Networks. PSYCHOMETRIKA 2022; 87:47-82. [PMID: 35192102 PMCID: PMC9021150 DOI: 10.1007/s11336-022-09848-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/27/2020] [Revised: 01/10/2022] [Accepted: 01/17/2022] [Indexed: 05/08/2023]
Abstract
The Ising model is one of the most widely analyzed graphical models in network psychometrics. However, popular approaches to parameter estimation and structure selection for the Ising model cannot naturally express uncertainty about the estimated parameters or selected structures. To address this issue, this paper offers an objective Bayesian approach to parameter estimation and structure selection for the Ising model. Our methods build on a continuous spike-and-slab approach. We show that our methods consistently select the correct structure and provide a new objective method to set the spike-and-slab hyperparameters. To circumvent the exploration of the complete structure space, which is too large in practical situations, we propose a novel approach that first screens for promising edges and then only explore the space instantiated by these edges. We apply our proposed methods to estimate the network of depression and alcohol use disorder symptoms from symptom scores of over 26,000 subjects.
Collapse
Affiliation(s)
- M Marsman
- University of Amsterdam, Psychological Methods, Nieuwe Achtergracht 129B, PO Box 15906, 1001 NK, Amsterdam, The Netherlands.
| | - K Huth
- University of Amsterdam, Psychological Methods, Nieuwe Achtergracht 129B, PO Box 15906, 1001 NK, Amsterdam, The Netherlands
- Centre for Urban Mental Health, Amsterdam, The Netherlands
| | - L J Waldorp
- University of Amsterdam, Psychological Methods, Nieuwe Achtergracht 129B, PO Box 15906, 1001 NK, Amsterdam, The Netherlands
| | - I Ntzoufras
- Athens University of Economics and Business, Athens, Greece
| |
Collapse
|
8
|
Kotekal S. Statistical limits of sparse mixture detection. Electron J Stat 2022. [DOI: 10.1214/22-ejs2053] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
Affiliation(s)
- Subhodh Kotekal
- Department of Statistics, University of Chicago, 5747 S. Ellis Avenue, Chicago, IL 60637, USA
| |
Collapse
|
9
|
Using network analysis to improve understanding and utility of the 10-item Autism-Spectrum Quotient. EXPERIMENTAL RESULTS 2022. [DOI: 10.1017/exp.2022.7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022] Open
Abstract
Abstract
The 10-item Autism-Spectrum Quotient (AQ10) is a measure of autistic traits used in research and clinical practice. Recently, the AQ10 has garnered critical attention, with research questioning its psychometric properties and clinical cutoff value. To help inform the utility of the measure, we conducted the first network analysis of the AQ10, with a view to gain a better understanding of its individual items. Using a large dataset of 6,595 participants who had completed the AQ10, we found strongest inter-subscale connections between communication, imagination, and socially relevant items. The nodes with greatest centrality concerned theory of mind differences. Together, these findings align with cognitive explanations of autism and provide clues about which AQ10 items show greatest utility for informing autism-related clinical practice.
Collapse
|
10
|
Katzenmajer-Pump L, Komáromy D, Balázs J. The importance of recognizing worthlessness for suicide prevention in adolescents with Attention-deficit/hyperactivity disorder. Front Psychiatry 2022; 13:969164. [PMID: 36458127 PMCID: PMC9705741 DOI: 10.3389/fpsyt.2022.969164] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/14/2022] [Accepted: 10/31/2022] [Indexed: 11/17/2022] Open
Abstract
BACKGROUND Attention-deficit/hyperactivity disorder (ADHD) is one of the most common psychiatric diagnoses among children and adolescents. Depression and general anxiety disorder (GAD) are often co-occurring with ADHD among children and adolescents. Previous studies have found that ADHD, depression and GAD are all strongly correlated with suicidal thoughts and planning. AIM The current study aimed to further explore the association between ADHD, GAD and depressive symptoms as well as their association with suicidal thoughts and planning among adolescents. METHOD Adolescents with ADHD diagnosis were involved from child psychiatry outpatient clinics and adolescents without a psychiatric treatment or diagnosis were enrolled from high schools in Hungary. The Mini International Neuropsychiatric Interview for Children and Adolescents was used to evaluate psychiatric symptoms and disorders as well as suicidal thoughts and planning. Regularized psychological networks were used to investigate the associations. RESULTS Altogether 185 adolescents (58 females and 127 males; mean age 14.79 years, SD = 1.48), 89 with ADHD and 96 without ADHD were enrolled. Depression symptom worthlessness was directly related to suicidal thoughts and planning, CI95 of the logit B between worthlessness and suicidal thought (0.72, 1.66). Both ADHD and anxiety were indirectly related to suicidal thoughts and planning through depression: CI95 of the logit B between being disorganized and feeling worthless is (0.38, 3.02), and CI95 of the logit B between being distressed and feeling worthless is (0.57, 2.52). CONCLUSIONS This study draws the attention of clinicians to the importance of recognizing "worthlessness" for suicide prevention in adolescents with ADHD. Furthermore, the results support previous studies, whereby symptoms of depression and anxiety mediate the relationship between ADHD and suicidal thoughts and planning. These results highlight the importance of ADHD comorbidities with depression and GAD and their effect on suicidal thoughts and planning.
Collapse
Affiliation(s)
- Luca Katzenmajer-Pump
- Doctoral School of Psychology, Institute of Psychology, Eötvös Loránd University, Budapest, Hungary
| | - Dániel Komáromy
- Department of Developmental and Clinical Child Psychology, Institute of Psychology, Eötvös Loránd University, Budapest, Hungary.,Department of Behavioral and Movement Sciences, Vrije Universiteit, Amsterdam, Netherlands.,Faculty of Social and Behavioural Sciences, University of Amsterdam, Amsterdam, Netherlands
| | - Judit Balázs
- Department of Developmental and Clinical Child Psychology, Institute of Psychology, Eötvös Loránd University, Budapest, Hungary.,Department of Psychology, Oslo New University College, Oslo, Norway
| |
Collapse
|
11
|
Calugi S, Dametti L, Chimini M, Dalle Grave A, Dalle Grave R. Change in eating-disorder psychopathology network structure in patients with anorexia nervosa treated with intensive cognitive behavior therapy. Int J Eat Disord 2021; 54:1800-1809. [PMID: 34331465 DOI: 10.1002/eat.23590] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/30/2021] [Revised: 06/23/2021] [Accepted: 07/22/2021] [Indexed: 11/08/2022]
Abstract
OBJECTIVE This study was designed to compare the change in eating-disorder feature networks in patients with anorexia nervosa after treatment with intensive enhanced cognitive behavior therapy (CBT-E). METHODS Patients seeking treatment for anorexia nervosa were consecutively recruited from January 2016 to September 2020. All patients aged ≥16 years who completed a 20-week intensive CBT-E program (13 weeks of inpatient followed by 7 weeks of day-hospital treatment) were included in the study. Body mass index (BMI) was measured, and the Eating Disorder Examination Questionnaire completed for each patient, both at baseline and the end of treatment. RESULTS The sample comprised 214 patients with anorexia nervosa. Treated patients showed significant improvements in BMI and eating-disorder psychopathology. Network analysis revealed a significant reduction in the network global and connection strengths at the end of treatment. The most central and highly interconnected nodes in the network at baseline were related to the drive for thinness, but at the end of treatment to body image concerns. Some edge connections were significantly stronger at baseline than at the end of treatment, while others were significantly stronger at the end of treatment than at baseline. DISCUSSION CBT-E reduces the psychopathology network connectivity over time in patients with anorexia nervosa. The differences in central nodes and edge connections between baseline and end of treatment, not detected by classical inferential analysis, may be informative for understanding the centrality of symptoms in the psychopathology network, and how a specific treatment may act to reduce symptoms and change their connections over time.
Collapse
Affiliation(s)
- Simona Calugi
- Department of Eating and Weight Disorders, Villa Garda Hospital, Garda, Italy
| | - Laura Dametti
- Department of Eating and Weight Disorders, Villa Garda Hospital, Garda, Italy
| | - Mirko Chimini
- Department of Eating and Weight Disorders, Villa Garda Hospital, Garda, Italy
| | - Anna Dalle Grave
- Department of Eating and Weight Disorders, Villa Garda Hospital, Garda, Italy
| | | |
Collapse
|
12
|
Furman SA, Stern AM, Uttam S, Taylor DL, Pullara F, Chennubhotla SC. In situ functional cell phenotyping reveals microdomain networks in colorectal cancer recurrence. CELL REPORTS METHODS 2021; 1:100072. [PMID: 34888541 PMCID: PMC8653984 DOI: 10.1016/j.crmeth.2021.100072] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/22/2021] [Revised: 06/14/2021] [Accepted: 08/09/2021] [Indexed: 04/21/2023]
Abstract
Tumors are dynamic ecosystems comprising localized niches (microdomains), possessing distinct compositions and spatial configurations of cancer and non-cancer cell populations. Microdomain-specific network signaling coevolves with a continuum of cell states and functional plasticity associated with disease progression and therapeutic responses. We present LEAPH, an unsupervised machine learning algorithm for identifying cell phenotypes, which applies recursive steps of probabilistic clustering and spatial regularization to derive functional phenotypes (FPs) along a continuum. Combining LEAPH with pointwise mutual information and network biology analyses enables the discovery of outcome-associated microdomains visualized as distinct spatial configurations of heterogeneous FPs. Utilization of an immunofluorescence-based (51 biomarkers) image dataset of colorectal carcinoma primary tumors (n = 213) revealed microdomain-specific network dysregulation supporting cancer stem cell maintenance and immunosuppression that associated selectively with the recurrence phenotype. LEAPH enables an explainable artificial intelligence platform providing insights into pathophysiological mechanisms and novel drug targets to inform personalized therapeutic strategies.
Collapse
Affiliation(s)
- Samantha A. Furman
- Department of Computational and Systems Biology, University of Pittsburgh, Pittsburgh, PA 15260, USA
| | - Andrew M. Stern
- Department of Computational and Systems Biology, University of Pittsburgh, Pittsburgh, PA 15260, USA
- University of Pittsburgh Drug Discovery Institute, University of Pittsburgh, Pittsburgh, PA 15261, USA
| | - Shikhar Uttam
- Department of Computational and Systems Biology, University of Pittsburgh, Pittsburgh, PA 15260, USA
| | - D. Lansing Taylor
- Department of Computational and Systems Biology, University of Pittsburgh, Pittsburgh, PA 15260, USA
- University of Pittsburgh Drug Discovery Institute, University of Pittsburgh, Pittsburgh, PA 15261, USA
- SpIntellx, Inc., 2425 Sidney Street, Pittsburgh, PA 15203, USA
| | - Filippo Pullara
- SpIntellx, Inc., 2425 Sidney Street, Pittsburgh, PA 15203, USA
| | - S. Chakra Chennubhotla
- Department of Computational and Systems Biology, University of Pittsburgh, Pittsburgh, PA 15260, USA
- University of Pittsburgh Drug Discovery Institute, University of Pittsburgh, Pittsburgh, PA 15261, USA
- SpIntellx, Inc., 2425 Sidney Street, Pittsburgh, PA 15203, USA
| |
Collapse
|
13
|
The influence of psychological network on the willingness to communicate in a second language. PLoS One 2021; 16:e0256644. [PMID: 34534221 PMCID: PMC8448313 DOI: 10.1371/journal.pone.0256644] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/10/2020] [Accepted: 08/11/2021] [Indexed: 11/19/2022] Open
Abstract
This study investigated the effect of the psychological network on the willingness to communicate in English among Japanese people. Previous studies have shown that psychological factors affect the willingness to communicate in English for Japanese people. However, the network structure of psychological factors and their effects have not been revealed yet. The present study conducted a network analysis with 644 Japanese people. Consequently, the edge between perceived communication competence and the willingness to communicate in the first or second language was very strong. Node centrality strength showed that these factors were central in the network structure. The results of the network analysis show the effect of psychological networks on the willingness to communicate in a second language, which will be beneficial for language education.
Collapse
|
14
|
Sinclair DG, Hooker G. An expectation maximization algorithm for high-dimensional model selection for the Ising model with misclassified states*. J Appl Stat 2021; 49:4049-4068. [DOI: 10.1080/02664763.2021.1970121] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
Affiliation(s)
- David G. Sinclair
- Department of Statistical Science, Cornell University, Ithaca, NY, USA
| | - Giles Hooker
- Department of Statistical Science, Cornell University, Ithaca, NY, USA
| |
Collapse
|
15
|
Ito T. The Influence of Socio-Ecological Networks on Willingness to Communicate in English for Japanese People. Front Psychol 2021; 12:580448. [PMID: 34305693 PMCID: PMC8299279 DOI: 10.3389/fpsyg.2021.580448] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2020] [Accepted: 06/16/2021] [Indexed: 11/25/2022] Open
Abstract
This study investigates the effect of socio-ecological networks on the willingness to communicate (WTC) in English among Japanese people. Previous studies have shown that relational mobility (socio-ecological factor), which is defined as the availability of opportunities to choose new relationship partners, positively affects the WTC in English for Japanese people. However, the network structure of the variables of relational mobility and its effects have not been revealed yet. The present study conducted network analysis with 474 Japanese university students and found the two clusters that correspond to the dimensions of relational mobility in the partial correlation network. Three variables regarding opportunities to meet new people and leave current relationships positively affected the WTC in English; one had a negative effect. Centrality indices, such as nodes strength, betweenness, and closeness, revealed the centrality of several variables in the network. Bootstrapping methods showed the trustworthiness of the estimated network structure and centrality indices as well as edges and variables whose effects differed significantly from that of others. Contrary to the regression analysis results, the network analysis findings can help us understand the in-depth effect of relational mobility on the WTC in a second language, which will prove useful for intervention studies.
Collapse
Affiliation(s)
- Takehiko Ito
- Department of Information Networking for Innovation and Design, Toyo University, Tokyo, Japan
| |
Collapse
|
16
|
Zhang R, Ren Z, Celedón JC, Chen W. Inference of large modified Poisson-type graphical models: Application to RNA-seq data in childhood atopic asthma studies. Ann Appl Stat 2021. [DOI: 10.1214/20-aoas1413] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
Affiliation(s)
- Rong Zhang
- Department of Statistics, University of Pittsburgh
| | - Zhao Ren
- Department of Statistics, University of Pittsburgh
| | - Juan C. Celedón
- Department of Pediatrics, UPMC Children’s Hospital of Pittsburgh, University of Pittsburgh
| | - Wei Chen
- Department of Pediatrics, UPMC Children’s Hospital of Pittsburgh, University of Pittsburgh
| |
Collapse
|
17
|
Epskamp S, Fried EI, van Borkulo CD, Robinaugh DJ, Marsman M, Dalege J, Rhemtulla M, Cramer AOJ. Investigating the Utility of Fixed-margin Sampling in Network Psychometrics. MULTIVARIATE BEHAVIORAL RESEARCH 2021; 56:314-328. [PMID: 30463456 DOI: 10.1080/00273171.2018.1489771] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/09/2017] [Revised: 06/04/2018] [Accepted: 06/05/2018] [Indexed: 06/09/2023]
Abstract
Steinley, Hoffman, Brusco, and Sher (2017) proposed a new method for evaluating the performance of psychological network models: fixed-margin sampling. The authors investigated LASSO regularized Ising models (eLasso) by generating random datasets with the same margins as the original binary dataset, and concluded that many estimated eLasso parameters are not distinguishable from those that would be expected if the data were generated by chance. We argue that fixed-margin sampling cannot be used for this purpose, as it generates data under a particular null-hypothesis: a unidimensional factor model with interchangeable indicators (i.e., the Rasch model). We show this by discussing relevant psychometric literature and by performing simulation studies. Results indicate that while eLasso correctly estimated network models and estimated almost no edges due to chance, fixed-margin sampling performed poorly in classifying true effects as "interesting" (Steinley et al. 2017, p. 1004). Further simulation studies indicate that fixed-margin sampling offers a powerful method for highlighting local misfit from the Rasch model, but performs only moderately in identifying global departures from the Rasch model. We conclude that fixed-margin sampling is not up to the task of assessing if results from estimated Ising models or other multivariate psychometric models are due to chance.
Collapse
Affiliation(s)
- Sacha Epskamp
- Department of Psychological Methods, University of Amsterdam, Amsterdam, The Netherlands
| | - Eiko I Fried
- Department of Psychological Methods, University of Amsterdam, Amsterdam, The Netherlands
| | - Claudia D van Borkulo
- Department of Psychological Methods, University of Amsterdam, Amsterdam, The Netherlands
| | - Donald J Robinaugh
- Department of Psychological Methods, University of Amsterdam, Amsterdam, The Netherlands
- Department of Psychiatry, Massachusetts General Hospital, Cambridge, MA, USA
| | - Maarten Marsman
- Department of Psychological Methods, University of Amsterdam, Amsterdam, The Netherlands
| | - Jonas Dalege
- Department of Social Psychology, University of Amsterdam, Amsterdam, The Netherlands
| | - Mijke Rhemtulla
- Department of Psychology, University of California, Davis, CA, USA
| | - Angélique O J Cramer
- Social and Behavioral Sciences, Department of Methodology and Statistics, Tilburg University, Tilburg, The Netherlands
| |
Collapse
|
18
|
Gyori D, Farkas BF, Horvath LO, Komaromy D, Meszaros G, Szentivanyi D, Balazs J. The Association of Nonsuicidal Self-Injury with Quality of Life and Mental Disorders in Clinical Adolescents-A Network Approach. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2021; 18:1840. [PMID: 33672808 PMCID: PMC7918829 DOI: 10.3390/ijerph18041840] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/10/2021] [Revised: 02/08/2021] [Accepted: 02/10/2021] [Indexed: 11/17/2022]
Abstract
Although earlier research has highlighted that psychiatric disorders significantly impair patients' quality of life (QoL), few studies have examined the relationship between nonsuicidal self-injury (NSSI) and QoL. Our aim was to investigate whether QoL mediates the mental disorder-NSSI relationship, and to study the QoL ratings agreement of self and parents in a clinical population of adolescents. We involved 202 adolescents from Vadaskert Child Psychiatric Hospital and Outpatient Clinic, Budapest, aged 13-18 years. All participants completed the Deliberate Self-Harm Inventory, Inventar zur Erfassung der Lebensqualität bei Kindern und Jugendlichen, and the Mini International Neuropsychiatric Interview Kid. To map the interrelationship between the NSSI, mental disorders, and QoL dimensions, Mixed Graphical Models were estimated. Adolescents with a history of NSSI rated their QoL to be significantly lower than adolescents without NSSI. Self and parents' QoL ratings are closer in the NSSI sample than in the no-NSSI sample. Among all QoL dimensions, only family problems had a direct significant association with NSSI engagement. Our results highlight that, contrary to our hypothesis, the presence of mental disorders mediates the relationship between most QoL dimensions and the occurrence of NSSI. Our results draw attention to the potential causal effect of environmental factors (e.g., peer problems) on mental disorders that, in turn, result in NSSI. The present paper highlights the importance of network modelling in clinical research.
Collapse
Affiliation(s)
- Dora Gyori
- Doctoral School of Psychology, Eotvos Lorand University, 1075 Budapest, Hungary; (L.O.H.); (D.S.)
- Institute of Psychology, Eotvos Lorand University, 1075 Budapest, Hungary; (D.K.); (J.B.)
| | - Bernadett Frida Farkas
- Mental Health Sciences Doctoral School, Semmelweis University, 1083 Budapest, Hungary; (B.F.F.); (G.M.)
| | - Lili Olga Horvath
- Doctoral School of Psychology, Eotvos Lorand University, 1075 Budapest, Hungary; (L.O.H.); (D.S.)
- Institute of Psychology, Eotvos Lorand University, 1075 Budapest, Hungary; (D.K.); (J.B.)
| | - Daniel Komaromy
- Institute of Psychology, Eotvos Lorand University, 1075 Budapest, Hungary; (D.K.); (J.B.)
- Faculty of Social and Behavioural Sciences, University of Amsterdam, 1018 WV Amsterdam, The Netherlands
- Department of Behavioural and Movement Sciences, Vrije Universiteit, 1081 HV Amsterdam, The Netherlands
| | - Gergely Meszaros
- Mental Health Sciences Doctoral School, Semmelweis University, 1083 Budapest, Hungary; (B.F.F.); (G.M.)
- Faculty of Medicine, Department of Psychiatry and Psychotherapy, Semmelweis University, 1083 Budapest, Hungary
| | - Dora Szentivanyi
- Doctoral School of Psychology, Eotvos Lorand University, 1075 Budapest, Hungary; (L.O.H.); (D.S.)
- Institute of Psychology, Eotvos Lorand University, 1075 Budapest, Hungary; (D.K.); (J.B.)
- Pedagogical Assistance Services, 1067 Budapest, Hungary
| | - Judit Balazs
- Institute of Psychology, Eotvos Lorand University, 1075 Budapest, Hungary; (D.K.); (J.B.)
- Department of Psychology, Bjørknes University College, 0456 Oslo, Norway
| |
Collapse
|
19
|
Responses to Stress: Investigating the Role of Gender, Social Relationships, and Touch Avoidance in Italy. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2021; 18:ijerph18020600. [PMID: 33445696 PMCID: PMC7828124 DOI: 10.3390/ijerph18020600] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/04/2020] [Revised: 01/03/2021] [Accepted: 01/10/2021] [Indexed: 12/12/2022]
Abstract
Stress is a physiological response to internal and external events we call “stressors”. Response to the same daily stressors varies across individuals and seems to be higher for women. A possible explanation for this phenomenon is that women perceive sociality, relationships, and intimacy—important sources of both stress and wellbeing—differently from how men experience them. In this study, we investigate how gender, attachment, and touch avoidance predict stress responses on a sample of 335 Italians (216 females; age = 35.82 ± 14.32). Moreover, we analyze the network of relationships between these variables through multiple linear regression and exploratory network analysis techniques. The results recontextualize the role of gender in determining stress responses in terms of (lack of) confidence and touch avoidance toward family members; attitudes toward relationships seem to be the main determinants of stress responses. These results have implications for reducing stress in both clinical settings and at a social level.
Collapse
|
20
|
Selig K, Shaw P, Ankerst D. Bayesian information criterion approximations to Bayes factors for univariate and multivariate logistic regression models. Int J Biostat 2020; 17:241-266. [PMID: 33119543 DOI: 10.1515/ijb-2020-0045] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/06/2020] [Accepted: 10/08/2020] [Indexed: 11/15/2022]
Abstract
Schwarz's criterion, also known as the Bayesian Information Criterion or BIC, is commonly used for model selection in logistic regression due to its simple intuitive formula. For tests of nested hypotheses in independent and identically distributed data as well as in Normal linear regression, previous results have motivated use of Schwarz's criterion by its consistent approximation to the Bayes factor (BF), defined as the ratio of posterior to prior model odds. Furthermore, under construction of an intuitive unit-information prior for the parameters of interest to test for inclusion in the nested models, previous results have shown that Schwarz's criterion approximates the BF to higher order in the neighborhood of the simpler nested model. This paper extends these results to univariate and multivariate logistic regression, providing approximations to the BF for arbitrary prior distributions and definitions of the unit-information prior corresponding to Schwarz's approximation. Simulations show accuracies of the approximations for small samples sizes as well as comparisons to conclusions from frequentist testing. We present an application in prostate cancer, the motivating setting for our work, which illustrates the approximation for large data sets in a practical example.
Collapse
Affiliation(s)
- Katharina Selig
- Department of Mathematics, Technical University of Munich, Munchen, Germany
| | - Pamela Shaw
- Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA
| | - Donna Ankerst
- Department of Mathematics, Technical University of Munich, Munchen, Germany
| |
Collapse
|
21
|
Breuer F, Greggersen W, Kahl KG, Schweiger U, Westermair AL. Caught in a web of trauma: Network analysis of childhood adversity and adult mental ill-health. CHILD ABUSE & NEGLECT 2020; 107:104534. [PMID: 32562964 DOI: 10.1016/j.chiabu.2020.104534] [Citation(s) in RCA: 16] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/28/2019] [Revised: 03/30/2020] [Accepted: 05/04/2020] [Indexed: 05/23/2023]
Abstract
BACKGROUND Current interventions for adverse childhood experiences have only limited effectiveness. OBJECTIVE We sought to identify optimal targets for the development of new interventions against adverse childhood experiences (ACE), that is, ACEs that a) are so central in the network of childhood adversity that curbing them is likely to impact other types of adversity, too, and b) are so central to the link of childhood adversity and adult mental ill-health that curbing them is likely to prevent this negative long-term effect from developing. PARTICIPANTS AND SETTING 384 adult psychiatric inpatients. METHODS Using the R packages qgraph and IsingFit, we analyzed the ACE network and the common network of ACEs and adult mental disorders. RESULTS We found two clusters of ACEs: direct interactions with the child and indirect traumatization via adverse circumstances. When controlling for interrelatedness, the associations of sexual abuse with posttraumatic stress disorder and borderline personality disorder were the only direct links between ACEs and adult mental disorders. CONCLUSIONS As neglect and violence against the mother were the most influential ACEs, curbing them is likely to destabilize the whole network of adversity. Thus, neglect and violence against the mother lend themselves as candidate targets for the development of new interventions. As sexual abuse was the only link between childhood adversity and adult mental ill-health, interventions against it seem most likely to keep this negative long-term effect from developing. Further, ideally prospective, research is needed to corroborate these findings.
Collapse
Affiliation(s)
- Fabian Breuer
- Department of Psychiatry and Psychotherapy, University of Lübeck, Lübeck, Germany
| | - Wiebke Greggersen
- Department of Psychiatry and Psychotherapy, University of Lübeck, Lübeck, Germany
| | - Kai G Kahl
- Department of Psychiatry, Social Psychiatry and Psychotherapy, Hannover Medical School, Hannover, Germany
| | - Ulrich Schweiger
- Department of Psychiatry and Psychotherapy, University of Lübeck, Lübeck, Germany
| | - Anna Lisa Westermair
- Department of Psychiatry and Psychotherapy, University of Lübeck, Lübeck, Germany.
| |
Collapse
|
22
|
Calugi S, Sartirana M, Misconel A, Boglioli C, Dalle Grave R. Eating disorder psychopathology in adults and adolescents with anorexia nervosa: A network approach. Int J Eat Disord 2020; 53:420-431. [PMID: 32314382 DOI: 10.1002/eat.23270] [Citation(s) in RCA: 20] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/20/2019] [Revised: 03/17/2020] [Accepted: 03/17/2020] [Indexed: 12/12/2022]
Abstract
OBJECTIVE The aim of this study was to assess and compare eating disorder feature networks in adult and adolescent patients with anorexia nervosa. METHODS Patients seeking treatment for anorexia nervosa in inpatient and outpatient settings were consecutively recruited from January 2008 to September 2019. Body mass index was measured, and each patient completed the Eating Disorder Examination Questionnaire. RESULTS The sample comprised 547 adolescent and 724 adult patients with anorexia nervosa. Network analysis showed that in both adults and adolescents, the most central and highly interconnected nodes in the network were related to shape overvaluation and desiring weight loss. The network comparison test identified similar global strength and network invariance, confirming the similarity of the two network structures. DISCUSSION The network structures in adult and adolescent patients with anorexia nervosa are similar, and lend weight to the cognitive behavioral theory that overvaluation of shape and weight is the core feature of anorexia nervosa psychopathology.
Collapse
Affiliation(s)
- Simona Calugi
- Department of Eating and Weight Disorders, Villa Garda Hospital, Garda, Italy
| | | | - Arianna Misconel
- Department of Eating and Weight Disorders, Villa Garda Hospital, Garda, Italy
| | - Camilla Boglioli
- Department of Eating and Weight Disorders, Villa Garda Hospital, Garda, Italy
| | | |
Collapse
|
23
|
Dalle Grave R, Soave F, Ruocco A, Dametti L, Calugi S. Quality of Life and Physical Performance in Patients with Obesity: A Network Analysis. Nutrients 2020; 12:E602. [PMID: 32110862 PMCID: PMC7146222 DOI: 10.3390/nu12030602] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2020] [Revised: 02/21/2020] [Accepted: 02/24/2020] [Indexed: 11/26/2022] Open
Abstract
BACKGROUND The aim of this study was to investigate the interconnections between specific quality-of-life domains in patients with obesity and high or low physical performance using a network approach. METHODS 716 consecutive female and male patients (aged 18-65 years) with obesity seeking weight-loss treatment were included. The 36-item Short Form Health Survey (SF-36) and the six-minute walking test (6MWT) were used to assess quality of life and physical performance, respectively. The sample was split into two groups according to the distance walked in the 6MWT. Network structures of the SF-36 domains in the two groups were assessed and compared, and the relative importance of individual items in the network structures was determined using centrality analyses. RESULTS 35.3% (n = 253) of participants covered more distance than expected, and 64.7% (n = 463) did not. Although low-performing patients showed lower quality of life domain scores, the network structures were similar in the two groups, with the SF-36 Vitality representing the central domain in both networks. Mental Health was a node with strong connections in patients who walked less distance. CONCLUSIONS These findings indicate that psychosocial variables represent the most influential and interconnected features as regards quality of life in both groups.
Collapse
Affiliation(s)
- Riccardo Dalle Grave
- Department of Eating and Weight Disorders, Villa Garda Hospital, 37138 Garda (VR), Italy; (F.S.); (A.R.); (L.D.); (S.C.)
| | | | | | | | | |
Collapse
|
24
|
Calugi S, Dalle Grave R. Psychological features in obesity: A network analysis. Int J Eat Disord 2020; 53:248-255. [PMID: 31657026 DOI: 10.1002/eat.23190] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/08/2019] [Revised: 10/04/2019] [Accepted: 10/07/2019] [Indexed: 01/13/2023]
Abstract
OBJECTIVE Enhanced understanding of psychosocial factors associated with obesity may improve knowledge of their interplay mechanisms. The aim of this study was to assess the relationship between psychosocial variables in individuals with obesity using a network analysis. METHODS Patients seeking treatment for obesity were consecutively recruited from a rehabilitative residential treatment program for severe obesity between January 2016 and March 2019. Each patient completed the following questionnaires: Eating Disorder Examination Questionnaire, Symptom Checklist-90, Obesity Related Well-Being, and Weight Bias Internalization Scale. In addition, current body mass index (BMI) was measured, and maximum acceptable and dream BMI were assessed. RESULTS The sample comprised 996 patients with obesity (age 52.3 [SD = 16.0] years; BMI 41.8 [SD = 7.8] kg/m2 ; 65.7% women; 52.2% married or living with a partner). Network analysis showed that interpersonal sensitivity and shape-weight concern, but also internalized weight stigma, were the most central and highly interconnected nodes in the network. In contrast, objective binge-eating episodes and dietary restraint were the most peripheral and least connected nodes. Eating disorder features and psychological distress formed two clearly separate clusters. No difference in network structure was found between men and women. CONCLUSIONS The pattern of network node connections supports the importance of assessing psychological distress, interpersonal sensitivity, shape-weight concern, and internalized weight stigma in patients seeking treatment for obesity.
Collapse
Affiliation(s)
- Simona Calugi
- Department of Eating and Weight Disorders, Villa Garda Hospital, Italy
| | | |
Collapse
|
25
|
Pensar J, Xu Y, Puranen S, Pesonen M, Kabashima Y, Corander J. High-dimensional structure learning of binary pairwise Markov networks: A comparative numerical study. Comput Stat Data Anal 2020. [DOI: 10.1016/j.csda.2019.06.012] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
26
|
Patterns of Anatomic Injury in Critically Injured Combat Casualties: A Network Analysis. Sci Rep 2019; 9:13767. [PMID: 31551454 PMCID: PMC6760527 DOI: 10.1038/s41598-019-50272-3] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2019] [Accepted: 08/30/2019] [Indexed: 11/12/2022] Open
Abstract
A mortality review of death caused by injury requires a determination of injury survivability prior to a determination of death preventability. If injuries are nonsurvivable, only non-medical primary prevention strategies have potential to prevent the death. Therefore, objective measures are needed to empirically inform injury survivability from complex anatomic patterns of injury. As a component of injury mortality reviews, network structures show promise to objectively elucidate survivability from complex anatomic patterns of injury resulting from explosive and firearm mechanisms. In this network analysis of 5,703 critically injured combat casualties, patterns of injury among fatalities from explosive mechanisms were associated with both a higher number and severity of anatomic injuries to regions such as the extremities, abdomen, and thorax. Patterns of injuries from a firearm were more isolated to individual body regions with fatal patterns involving more severe injuries to the head and thorax. Each injury generates a specific level of risk as part of an overall anatomic pattern to inform injury survivability not always captured by traditional trauma scoring systems. Network models have potential to further elucidate differences between potentially survivable and nonsurvivable anatomic patterns of injury as part of the mortality review process relevant to improving both the military and civilian trauma care systems.
Collapse
|
27
|
Piccirillo ML, Rodebaugh TL. Foundations of idiographic methods in psychology and applications for psychotherapy. Clin Psychol Rev 2019; 71:90-100. [PMID: 30665765 PMCID: PMC11130566 DOI: 10.1016/j.cpr.2019.01.002] [Citation(s) in RCA: 54] [Impact Index Per Article: 10.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/08/2018] [Revised: 01/08/2019] [Accepted: 01/12/2019] [Indexed: 01/30/2023]
Abstract
Researchers have long called for greater recognition and use of longitudinal, individual-level research in the study of psychopathology and psychotherapy. Much of our current research attempts to indirectly investigate individual-level, or idiographic, psychological processes via group-based, or nomothetic, designs. However, results from nomothetic research do not necessarily translate to the individual-level. In this review, we discuss how idiographic analyses can be integrated into psychotherapy and psychotherapy research. We examine and review key statistical methods for conducting idiographic analyses. These methods include factor-based and vector autoregressive approaches using longitudinal data. The theoretical framework behind each approach is reviewed and critically evaluated. Empirical examples of each approach are discussed, with the aim of helping interested readers consider how they may use idiographic methods to analyze longitudinal data and psychological processes. Finally, we conclude by citing key limitations of the idiographic approach, calling for greater development of these analyses to ease their successful integration into clinical settings.
Collapse
Affiliation(s)
- Marilyn L Piccirillo
- Department of Psychological and Brain Sciences, Washington University in St. Louis, USA.
| | - Thomas L Rodebaugh
- Department of Psychological and Brain Sciences, Washington University in St. Louis, USA
| |
Collapse
|
28
|
Network structure of the Wisconsin Schizotypy Scales-Short Forms: Examining psychometric network filtering approaches. Behav Res Methods 2019. [PMID: 29520631 DOI: 10.3758/s13428-018-1032-9] [Citation(s) in RCA: 36] [Impact Index Per Article: 7.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
Schizotypy is a multidimensional construct that provides a useful framework for understanding the etiology, development, and risk for schizophrenia-spectrum disorders. Past research has applied traditional methods, such as factor analysis, to uncovering common dimensions of schizotypy. In the present study, we aimed to advance the construct of schizotypy, measured by the Wisconsin Schizotypy Scales-Short Forms (WSS-SF), beyond this general scope by applying two different psychometric network filtering approaches-the state-of-the-art approach (lasso), which has been employed in previous studies, and an alternative approach (information-filtering networks; IFNs). First, we applied both filtering approaches to two large, independent samples of WSS-SF data (ns = 5,831 and 2,171) and assessed each approach's representation of the WSS-SF's schizotypy construct. Both filtering approaches produced results similar to those from traditional methods, with the IFN approach producing results more consistent with previous theoretical interpretations of schizotypy. Then we evaluated how well both filtering approaches reproduced the global and local network characteristics of the two samples. We found that the IFN approach produced more consistent results for both global and local network characteristics. Finally, we sought to evaluate the predictability of the network centrality measures for each filtering approach, by determining the core, intermediate, and peripheral items on the WSS-SF and using them to predict interview reports of schizophrenia-spectrum symptoms. We found some similarities and differences in their effectiveness, with the IFN approach's network structure providing better overall predictive distinctions. We discuss the implications of our findings for schizotypy and for psychometric network analysis more generally.
Collapse
|
29
|
Cai TT, Li H, Ma J, Xia Y. Differential Markov random field analysis with an application to detecting differential microbial community networks. Biometrika 2019; 106:401-416. [PMID: 31097834 DOI: 10.1093/biomet/asz012] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/11/2017] [Indexed: 11/12/2022] Open
Abstract
Micro-organisms such as bacteria form complex ecological community networks that can be greatly influenced by diet and other environmental factors. Differential analysis of microbial community structures aims to elucidate systematic changes during an adaptive response to changes in environment. In this paper, we propose a flexible Markov random field model for microbial network structure and introduce a hypothesis testing framework for detecting differences between networks, also known as differential network analysis. Our global test for differential networks is particularly powerful against sparse alternatives. In addition, we develop a multiple testing procedure with false discovery rate control to identify the structure of the differential network. The proposed method is applied to data from a gut microbiome study on U.K. twins to evaluate how age affects the microbial community network.
Collapse
Affiliation(s)
- T T Cai
- Department of Statistics, University of Pennsylvania, 3720 Walnut Street, Philadelphia, Pennsylvania 19104, USA
| | - H Li
- Department of Biostatistics, University of Pennsylvania, 423 Guardian Drive, Philadelphia, Pennsylvania 19104, USA
| | - J Ma
- Department of Biostatistics, University of Pennsylvania, 423 Guardian Drive, Philadelphia, Pennsylvania 19104, USA
| | - Y Xia
- Department of Statistics, School of Management, Fudan University, Shanghai 200433, China
| |
Collapse
|
30
|
Coêlho BM, Santana GL, Duarte-Guerra LS, Viana MC, Neto FL, Andrade LH, Wang YP. The role of gender in the structure of networks of childhood adversity. Psychiatry Res 2018; 270:348-356. [PMID: 30293013 DOI: 10.1016/j.psychres.2018.09.059] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/05/2018] [Revised: 08/16/2018] [Accepted: 09/25/2018] [Indexed: 11/27/2022]
Abstract
The objective of present study is to investigate the relationship between different childhood adversities. The potential impact of early adversity on prevention programs is discussed. Data on twelve childhood adversities was collected from a representative sample of 5037 members of the general population living in a large metropolitan area. Data were analyzed through network analysis, to estimate and compare network connectivity and centrality measures by gender. Over half the respondents had been exposed to at least one adversity during their earlier developmental stage. Among adversity-exposed persons, 48.4% presented simultaneous adversities, most of which were related to 'family dysfunction' and 'maltreatment' (mean = 2.9 adversities). Women reported more adversities than men (59.0% vs. 47.6%). Although the 'global' network connectivity across adversities was similar in both genders, 'regional' distinctions in the network structure were found. While 'neglect' and 'parental death' were more important for women than men, 'parental mental disorders' was more important for men. Gender-related childhood adversities were clustered experiences. Adversities related to 'early family dysfunction' and 'maltreatment' were prominent features in the networks of both boys and girls. Differential preventive and intervention programs should take into account gender-related patterns of exposure and reporting patterns of early adversity.
Collapse
Affiliation(s)
- Bruno Mendonça Coêlho
- Nucleo de Epidemiologia Psiquiatrica (LIM-23), Instituto de Psiquiatria, Hospital das Clinicas HCFMUSP, Faculdade de Medicina, Universidade de Sao Paulo, Sao Paulo, SP, Brazil; Departamento de Psiquiatria, Faculdade de Medicina (FMUSP), Universidade de Sao Paulo, Sao Paulo, SP, Brazil.
| | - Geilson Lima Santana
- Nucleo de Epidemiologia Psiquiatrica (LIM-23), Instituto de Psiquiatria, Hospital das Clinicas HCFMUSP, Faculdade de Medicina, Universidade de Sao Paulo, Sao Paulo, SP, Brazil
| | - Leorides Severo Duarte-Guerra
- Nucleo de Epidemiologia Psiquiatrica (LIM-23), Instituto de Psiquiatria, Hospital das Clinicas HCFMUSP, Faculdade de Medicina, Universidade de Sao Paulo, Sao Paulo, SP, Brazil
| | - Maria Carmen Viana
- Department of Social Medicine Post-Graduate Program in Public Health, Health Sciences Center, Universidade Federal do Espírito Santo, Vitória, ES, Brazil
| | - Francisco Lotufo Neto
- Departamento de Psiquiatria, Faculdade de Medicina (FMUSP), Universidade de Sao Paulo, Sao Paulo, SP, Brazil
| | - Laura Helena Andrade
- Nucleo de Epidemiologia Psiquiatrica (LIM-23), Instituto de Psiquiatria, Hospital das Clinicas HCFMUSP, Faculdade de Medicina, Universidade de Sao Paulo, Sao Paulo, SP, Brazil
| | - Yuan-Pang Wang
- Nucleo de Epidemiologia Psiquiatrica (LIM-23), Instituto de Psiquiatria, Hospital das Clinicas HCFMUSP, Faculdade de Medicina, Universidade de Sao Paulo, Sao Paulo, SP, Brazil
| |
Collapse
|
31
|
Pelowski M, Leder H, Mitschke V, Specker E, Gerger G, Tinio PPL, Vaporova E, Bieg T, Husslein-Arco A. Capturing Aesthetic Experiences With Installation Art: An Empirical Assessment of Emotion, Evaluations, and Mobile Eye Tracking in Olafur Eliasson's "Baroque, Baroque!". Front Psychol 2018; 9:1255. [PMID: 30127756 PMCID: PMC6088181 DOI: 10.3389/fpsyg.2018.01255] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2018] [Accepted: 06/29/2018] [Indexed: 11/13/2022] Open
Abstract
Installation art is one of the most important and provocative developments in the visual arts during the last half century and has become a key focus of artists and of contemporary museums. It is also seen as particularly challenging or even disliked by many viewers, and—due to its unique in situ, immersive setting—is equally regarded as difficult or even beyond the grasp of present methods in empirical aesthetic psychology. In this paper, we introduce an exploratory study with installation art, utilizing a collection of techniques to capture the eclectic, the embodied, and often the emotionally-charged viewing experience. We present results from an investigation of two pieces, both part of Olafur Eliasson’s exhibition “Baroque, Baroque” held at the Belvedere museum in Vienna. These were assessed by pre- and post-viewing questionnaires focusing on emotion, meaning-making, and appraisals, in tandem with mobile eye tracking to consider viewers’ attention to both installed artworks and/or to the museum environment. The data showed differences in participants’ emotional states, appraisals, and visual exploration, which together paint a picture of the aesthetic reactions to the works. These differences also showed how viewers’ appraisal strategies, meaning making, and physical actions facilitated relatively more or less deep engagement with, and enjoyment of, the art. The results are discussed in terms of their implications for museum studies, art education, and theory in empirical aesthetics.
Collapse
Affiliation(s)
- Matthew Pelowski
- Department of Basic Psychological Research and Research Methods, Faculty of Psychology, University of Vienna, Vienna, Austria
| | - Helmut Leder
- Department of Basic Psychological Research and Research Methods, Faculty of Psychology, University of Vienna, Vienna, Austria
| | - Vanessa Mitschke
- Department of Basic Psychological Research and Research Methods, Faculty of Psychology, University of Vienna, Vienna, Austria.,Department of General Psychology II, University of Würzburg, Würzburg, Germany
| | - Eva Specker
- Department of Basic Psychological Research and Research Methods, Faculty of Psychology, University of Vienna, Vienna, Austria
| | - Gernot Gerger
- Department of Basic Psychological Research and Research Methods, Faculty of Psychology, University of Vienna, Vienna, Austria.,Department of Psychology, Webster Vienna Private University, Vienna, Austria
| | - Pablo P L Tinio
- Department of Educational Foundations, Montclair State University, Montclair, NJ, United States
| | - Elena Vaporova
- Department of Basic Psychological Research and Research Methods, Faculty of Psychology, University of Vienna, Vienna, Austria
| | - Till Bieg
- Department of Basic Psychological Research and Research Methods, Faculty of Psychology, University of Vienna, Vienna, Austria.,Center for Technology Experience, AIT Austrian Institute of Technology, Vienna, Austria
| | | |
Collapse
|
32
|
Bell V, O'Driscoll C. The network structure of paranoia in the general population. Soc Psychiatry Psychiatr Epidemiol 2018; 53:737-744. [PMID: 29427197 PMCID: PMC6003969 DOI: 10.1007/s00127-018-1487-0] [Citation(s) in RCA: 42] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/01/2017] [Accepted: 01/21/2018] [Indexed: 12/25/2022]
Abstract
PURPOSE Bebbington and colleagues' influential study on 'the structure of paranoia in the general population' used data from the British National Psychiatric Morbidity Survey and latent variable analysis methods. Network analysis is a relatively new approach in psychopathology research that considers mental disorders to be emergent phenomena from causal interactions among symptoms. This study re-analysed the British National Psychiatric Morbidity Survey data using network analysis to examine the network structure of paranoia in the general population. METHODS We used a Graphical Least Absolute Shrinkage and Selection Operator (glasso) method that estimated an optimal network structure based on the Extended Bayesian Information Criterion. Network sub-communities were identified by spinglass and EGA algorithms and centrality metrics were calculated per item and per sub-community. RESULTS We replicated Bebbington's four component structure of paranoia, identifying 'interpersonal sensitivities', 'mistrust', 'ideas of reference' and 'ideas of persecution' as sub-communities in the network. In line with previous experimental findings, worry was the most central item in the network. However, 'mistrust' and 'ideas of reference' were the most central sub-communities. CONCLUSIONS Rather than a strict hierarchy, we argue that the structure of paranoia is best thought of as a heterarchy, where the activation of high-centrality nodes and communities is most likely to lead to steady state paranoia. We also highlight the novel methodological approach used by this study: namely, using network analysis to re-examine a population structure of psychopathology previously identified by latent variable approaches.
Collapse
Affiliation(s)
- Vaughan Bell
- Division of Psychiatry, University College London, 6th Floor, Maple House, 149 Tottenham Court Road, London, W1T 7NF, UK.
- South London and Maudsley NHS Foundation Trust, London, UK.
| | - Ciarán O'Driscoll
- Division of Psychiatry, University College London, 6th Floor, Maple House, 149 Tottenham Court Road, London, W1T 7NF, UK
- North East London NHS Foundation Trust, London, UK
| |
Collapse
|
33
|
Jayawickreme N, Mootoo C, Fountain C, Rasmussen A, Jayawickreme E, Bertuccio RF. Post-conflict struggles as networks of problems: A network analysis of trauma, daily stressors and psychological distress among Sri Lankan war survivors. Soc Sci Med 2017; 190:119-132. [PMID: 28858697 PMCID: PMC5607106 DOI: 10.1016/j.socscimed.2017.08.027] [Citation(s) in RCA: 27] [Impact Index Per Article: 3.9] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2017] [Revised: 08/18/2017] [Accepted: 08/21/2017] [Indexed: 01/08/2023]
Abstract
A growing body of literature indicates that the mental distress experienced by survivors of war is a function of both experienced trauma and stressful life events. However, the majority of these studies are limited in that they 1) employ models of psychological distress that emphasize underlying latent constructs and do not allow researchers to examine the unique associations between particular symptoms and various stressors; and 2) use one or more measures that were not developed for that particular context and thus may exclude key traumas, stressful life events and symptoms of psychopathology. The current study addresses both these limitations by 1) using a novel conceptual model, network analysis, which assumes that symptoms covary with each other not because they stem from a latent construct, but rather because they represent meaningful relationships between the symptoms; and 2) employing a locally developed measure of experienced trauma, stressful life problems and symptoms of psychopathology. Over the course of 2009-2011, 337 survivors of the Sri Lankan civil war were administered the Penn-RESIST-Peradeniya War Problems Questionnaire (PRPWPQ). Network analysis revealed that symptoms of psychopathology, problems pertaining to lack of basic needs, and social problems were central to the network relative to experienced trauma and other types of problems. After controlling for shared associations, social problems in particular were the most central, significantly more so than traumatic events and family problems. Several particular traumatic events, stressful life events and symptoms of psychopathology that were central to the network were also identified. Discussion emphasizes the utility of such network models to researchers and practitioners determining how to spend limited resources in the most impactful way possible.
Collapse
Affiliation(s)
| | - Candace Mootoo
- Department of Psychology, Fordham University, New York, NY, USA
| | | | | | | | | |
Collapse
|
34
|
Atchadé YA. On the contraction properties of some high-dimensional quasi-posterior distributions. Ann Stat 2017. [DOI: 10.1214/16-aos1526] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|
35
|
Marchetti GM, Wermuth N. Explicit, identical maximum likelihood estimates for some cyclic Gaussian and cyclic Ising models. Stat (Int Stat Inst) 2017. [DOI: 10.1002/sta4.155] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
Affiliation(s)
- Giovanni M. Marchetti
- Department of Statistics, Computer Science, Applications “G. Parenti”; University of Florence; viale Morgagni 59 Florence 50134 Italy
| | - Nanny Wermuth
- Mathematical Sciences; Chalmers University of Technology; Gothenburg SE-412 96 Sweden
- Department of Medical Psychology and Medical Sociology; Johannes Gutenberg University of Mainz; Saarstrasse 21 Mainz 55099 Germany
| |
Collapse
|
36
|
Epskamp S, Kruis J, Marsman M. Estimating psychopathological networks: Be careful what you wish for. PLoS One 2017; 12:e0179891. [PMID: 28644856 PMCID: PMC5482475 DOI: 10.1371/journal.pone.0179891] [Citation(s) in RCA: 136] [Impact Index Per Article: 19.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2016] [Accepted: 06/02/2017] [Indexed: 01/26/2023] Open
Abstract
Network models, in which psychopathological disorders are conceptualized as a complex interplay of psychological and biological components, have become increasingly popular in the recent psychopathological literature (Borsboom, et. al., 2011). These network models often contain significant numbers of unknown parameters, yet the sample sizes available in psychological research are limited. As such, general assumptions about the true network are introduced to reduce the number of free parameters. Incorporating these assumptions, however, means that the resulting network will lead to reflect the particular structure assumed by the estimation method-a crucial and often ignored aspect of psychopathological networks. For example, observing a sparse structure and simultaneously assuming a sparse structure does not imply that the true model is, in fact, sparse. To illustrate this point, we discuss recent literature and show the effect of the assumption of sparsity in three simulation studies.
Collapse
Affiliation(s)
- Sacha Epskamp
- Department of Psychological Methods, University of Amsterdam, Amsterdam, The Netherlands
| | - Joost Kruis
- Department of Psychological Methods, University of Amsterdam, Amsterdam, The Netherlands
| | - Maarten Marsman
- Department of Psychological Methods, University of Amsterdam, Amsterdam, The Netherlands
| |
Collapse
|
37
|
|
38
|
Lin L, Drton M, Shojaie A. Estimation of High-Dimensional Graphical Models Using Regularized Score Matching. Electron J Stat 2016; 10:806-854. [PMID: 28638498 PMCID: PMC5476334 DOI: 10.1214/16-ejs1126] [Citation(s) in RCA: 20] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/06/2023]
Abstract
Graphical models are widely used to model stochastic dependences among large collections of variables. We introduce a new method of estimating undirected conditional independence graphs based on the score matching loss, introduced by Hyvärinen (2005), and subsequently extended in Hyvärinen (2007). The regularized score matching method we propose applies to settings with continuous observations and allows for computationally efficient treatment of possibly non-Gaussian exponential family models. In the well-explored Gaussian setting, regularized score matching avoids issues of asymmetry that arise when applying the technique of neighborhood selection, and compared to existing methods that directly yield symmetric estimates, the score matching approach has the advantage that the considered loss is quadratic and gives piecewise linear solution paths under ℓ1 regularization. Under suitable irrepresentability conditions, we show that ℓ1-regularized score matching is consistent for graph estimation in sparse high-dimensional settings. Through numerical experiments and an application to RNAseq data, we confirm that regularized score matching achieves state-of-the-art performance in the Gaussian case and provides a valuable tool for computationally efficient estimation in non-Gaussian graphical models.
Collapse
Affiliation(s)
- Lina Lin
- Department of Statistics, University of Washington, Seattle, WA 98195, U.S.A
| | - Mathias Drton
- Department of Statistics, University of Washington, Seattle, WA 98195, U.S.A
| | - Ali Shojaie
- Department of Biostatistics, University of Washington, Seattle, WA 98195, U.S.A
| |
Collapse
|
39
|
Barber RF, Drton M. High-dimensional Ising model selection with Bayesian information criteria. Electron J Stat 2015. [DOI: 10.1214/15-ejs1012] [Citation(s) in RCA: 46] [Impact Index Per Article: 5.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|