Mark Huisman

Software for social network analysis

Introduction This chapter reviews software for the analysis of social networks. Both commercial and freely available packages are considered. Based on the software page on the INSNA website (http://www.insna.org/INSNA/soft inf.html), and using the main topics in the book on network analysis by Wasserman and Faust (1994), which we regard as the standard text, we selected twenty-seven software packages: twenty-three stand-alone programs, listed in Table 13.1.1, and five utility toolkits given in Table 13.1.2. Software merely aimed at visualization of networks was not admitted to the list because this is the topic of Chapter 12 of this book (Freeman 2004). We do review a few programs with strong visualization properties. Some were originally developed for network visualization, and now contain analysis procedures (e.g., NetDraw; Borgatti 2002). Other programs were specifically developed to integrate network analysis and visualization (e.g., NetMiner, Cyram 2004, and visone; Brandes and Wagner 2003). Two other programs for network visualization are worth mentioning here because some of the reviewed software packages have export functions to these graph drawing programs, or they are freely distributed together with the social analysis software: KrackPlot (Krackhardt, Blythe, and McGrath 1994) and Mage (Richardson 2001). The age of the software was not a criterion for selection, although the release dates of the last versions of the majority of the reviewed software were within the last one or two years. Tables 13.1.1 and 13.1.2 describe the main objective or characteristic of each program.

Statistical Analysis of Longitudinal Network Data with Changing Composition

Markov chains can be used for the modeling of complex longitudinal network data. One class of probability models to model the evolution of social networks are stochastic actor-oriented models for network change proposed by Snijders. These models are continuous-time Markov chain models that are implemented as simulation models. The authors propose an extension of the simulation algorithm of stochastic actor-oriented models to include networks of changing composition. In empirical research, the composition of networks may change due to actors joining or leaving the network at some point in time. The composition changes are modeled as exogenous events that occur at given time points and are implemented in the simulation algorithm. The estimation of the network effects, as well as the effects of actor and dyadic attributes that influence the evolution of the network, is based on the simulation of Markov chains.

Treatment of non-response in longitudinal network studies

The collection of longitudinal data on complete social networks often faces the problem of actor nonresponse. The resulting incomplete data pose a challenge to statistical analysis, as there typically is no natural way to treat the missing cases. This paper examines the problems caused by actors missing as nominators, but still occurring as nominees, in complete, directed networks measured in a panel design. In the framework of stochastic actor-driven models for network change (“SIENA models”), different methods to cope with such incomplete data are investigated. Data on a friendship network among female high school students are used to illustrate the procedures. Missing data problems related to early panel exit and late panel entry are not addressed.

Burnout and engagement among resident doctors in the Netherlands: a national study

Medical Education 2010: 44 : 236–247

Is a combined therapy more effective than either CBT or SSRI alone? Results of a multicenter trial on panic disorder with or without agoraphobia

Objective:  To establish whether the combination of cognitive‐behavioral therapy (CBT) and pharmacotherapy (SSRI) was more effective in treating panic disorder (PD) than either CBT or SSRI alone, and to evaluate any differential effects between the mono‐treatments.

Imputation of missing scale data with item response models

Confronted with incomplete data due to nonresponse, a researcher may want to impute missing values to estimate latent properties of respondents. In this chapter the results of a simulation study are presented, investigating the performance of several imputation techniques. Some imputation procedures are based on item response theory (IRT) models, which can also be used to estimate latent abilities directly from the incomplete data by using incomplete testing designs when data are missing by design. This strategy has some serious disadvantages in the case of item nonresponse, because nonresponse is assumed to be ignorable and computational problems arise in scales with many items. In a second simulation study, the performance of some imputation techniques is compared to the incomplete design strategy, in the case of item nonresponse. The latter strategy results in slightly better ability estimates, but imputation is almost as good, especially when it is based on IRT models.

Trajectories of Psychosocial Problems in Adolescents Predicted by Findings From Early Well-Child Assessments

PURPOSE To describe trajectories of emotional and behavioral problems in adolescents and to identify early indicators of these trajectories using data from routine well-child assessments at ages 0-4 years. METHODS Data from three assessment waves of adolescents (n = 1,816) of the TRAILS were used (ages: 11-17 years). Information on early indicators (at ages 0-4 years) came from the records of the well-child services. Trajectories of emotional and behavioral problems were based on the parent-reported Child Behavior Checklist and the adolescent-reported Youth Self-Report, filled out at ages 11, 14, and 17 years. Multinomial logistic regression analysis was used to examine the predictive value of these early indicators on trajectories. RESULTS For boys and girls, we found four trajectories for each outcome: one with high problem levels, and three with middle-high, middle-low, and low levels. For emotional problems, the type of trajectory was predicted by parental educational level and parental divorce or single parents, for both genders. Moreover, sleep problems were predictive in boys and language problems in girls (odds ratios between 1.53 and 7.42). For behavioral problems, the type of trajectory was predicted by maternal smoking during pregnancy, parental educational level, and parental divorce or single parents, for both genders. Moreover, for boys, early behavioral problems and attention hyperactivity problems were predictive (odds ratios between 1.64 and 5.43). CONCLUSIONS Trajectories of emotional and behavioral problems during adolescence are rather stable and can be predicted by a parsimonious set of data from early well-child assessments.

Handling Missing Data by Re-approaching Non-respondents

When handling missing data, a researcher should be aware of the mechanism underlying the missingness. In the presence of non-randomly missing data, a model of the missing data mechanism should be included in the analyses to prevent the analyses based on the data from becoming biased. Modeling the missing data mechanism, however, is a difficult task. One way in which knowledge about the missing data mechanism may be obtained is by collecting additional data from non-respondents. In this paper the method of re-approaching respondents who did not answer all questions of a questionnaire is described. New answers were obtained from a sample of these non-respondents and the reason(s) for skipping questions was (were) probed for. The additional data resulted in a larger sample and was used to investigate the differences between respondents and non-respondents, whereas probing for the causes of missingness resulted in more knowledge about the nature of the missing data patterns.

Stimulating Intersubjective Communication in an Adult with Deafblindness : A Single-Case Experiment

Sensory disabilities may limit a persons development of intersubjectivity, that is, the awareness of self and other, which develops in conjunction with interpersonal communication. This study used intersubjectivity theory to test a new intervention called the High-Quality Communication (HQC) intervention for its effects on a young adult with congenital deafblindness and a developmental age of between 1.5 and 4 years. Three of his social partners were trained to support attunement and meaning making with him through education and video feedback. This study measured seven observation categories at three layers of intersubjective development during a baseline and two intervention phases: dyadic interaction, shared emotion, referential communication, meaning negotiation, shared meaning, declarative communication, and shared past experience. The participants use of conventional communication was included as an additional category. Effects were observed in all observation categories from the baseline to the intervention phases. Further study of the effectiveness of the HQC intervention is recommended to test whether effects generalize across people and settings.

Revenge and psychological adjustment after homicidal loss

Feelings of revenge are a common human response to being hurt by others. Among crime victims of severe sexual or physical violence, significant correlations have been reported between revenge and Posttraumatic Stress Disorder (PTSD). Homicide is one of the most severe forms of interpersonal violence. It is therefore likely that individuals bereaved by homicide experience high levels of revenge, which may hamper efforts to cope with traumatic loss. The relationship between revenge and psychological adjustment following homicidal loss has not yet been empirically examined. In the current cross-sectional study, we used self-report data from 331 spouses, family members and friends of homicide victims to examine the relationships between dispositional revenge and situational revenge on the one hand and symptom-levels of PTSD and complicated grief, as well as indices of positive functioning, on the other hand. Furthermore, the association between revenge and socio-demographic and offense-related factors was examined. Participants were recruited from a governmental support organization, a website with information for homicidally bereaved individuals, and members of support groups. Levels of both dispositional and situational revenge were positively associated with symptoms of PTSD and complicated grief, and negatively with positive functioning. Participants reported significantly less situational revenge in cases where the perpetrator was a direct family member than cases where the perpetrator was an indirect family member, friend, or someone unknown. Homicidally bereaved individuals reported more situational revenge, but not more dispositional revenge than a sample of students who had experienced relatively mild interpersonal transgressions.