Kelly M. Harrington

Sample Size Requirements for Structural Equation Models An Evaluation of Power, Bias, and Solution Propriety

Determining sample size requirements for structural equation modeling (SEM) is a challenge often faced by investigators, peer reviewers, and grant writers. Recent years have seen a large increase in SEMs in the behavioral science literature, but consideration of sample size requirements for applied SEMs often relies on outdated rules-of-thumb. This study used Monte Carlo data simulation techniques to evaluate sample size requirements for common applied SEMs. Across a series of simulations, we systematically varied key model properties, including number of indicators and factors, magnitude of factor loadings and path coefficients, and amount of missing data. We investigated how changes in these parameters affected sample size requirements with respect to statistical power, bias in the parameter estimates, and overall solution propriety. Results revealed a range of sample size requirements (i.e., from 30 to 460 cases), meaningful patterns of association between parameters and sample size, and highlight the limitations of commonly cited rules-of-thumb. The broad “lessons learned” for determining SEM sample size requirements are discussed.

Personality-based latent classes of posttraumatic psychopathology: personality disorders and the internalizing/externalizing model.

Prior research using the Brief Form of the Multidimensional Personality Questionnaire (MPQ-BF; Patrick, Curtin, & Tellegen, 2002) has shown evidence of 3 temperament-based subtypes--termed internalizing, externalizing, and simple PTSD--among individuals with symptoms of posttraumatic stress disorder (PTSD; Miller, Greif, & Smith, 2003). This study sought to replicate and extend research in this area by conducting a latent profile analysis of higher order temperament scales from the MPQ-BF using a new sample of 208 veterans with symptoms of PTSD. Results suggest that a 3-class solution reflecting internalizing, externalizing, and simple subtypes of posttraumatic psychopathology provided the best fit to the data. The externalizing subtype was characterized by features of antisocial, borderline, histrionic, and narcissistic personality disorders on the International Personality Disorder Examination (Loranger, 1999) as well as low levels of constraint and high levels of negative emotionality on the MPQ-BF. In contrast, individuals in the internalizing class exhibited features of schizoid and avoidant personality disorders, low levels of positive emotionality, and high levels of negative emotionality. The simple subtype was defined by low levels of comorbid personality disorder features and relatively normal personality profiles. Findings support the reliability of this typology and support the relevance of the internalizing and externalizing model to the structure of personality disorders.

An evaluation of competing models for the structure of PTSD symptoms using external measures of comorbidity

Research on the structure of posttraumatic stress disorder (PTSD) symptoms has yielded support for two 4-factor models: the King (King, Leskin, King, & Weathers, 1998) and Simms/Watson models (Simms, Watson, & Doebbeling, 2002). This study evaluated them using data drawn from 1,128 Vietnam veterans by comparing associations with a latent internalizing comorbidity variable and five scales from the MMPI-2 Restructured Clinical (RC) Scales (Tellegen et al., 2003). The Simms/Watson dysphoria factor failed to show evidence of superior convergent or discriminant validity in association with external measures relative to the numbing or hyperarousal factors of the King model. Findings raise questions about proposals to abandon the distinction between numbing and hyperarousal symptoms in favor of a dysphoria-based model.

PTSD and conflict behavior between veterans and their intimate partners.

This study examined the influence of trauma history and PTSD symptoms on the behavior of veterans and their intimate partners (287 couples; N=574) observed during conflict discussions and coded using the Rapid Marital Interaction Coding System (Heyman, 2004). Dyadic structural equation modeling analyses showed that PTSD was associated with more frequent displays of hostility and psychological abuse and fewer expressions of acceptance and humor in both veterans and their partners. Findings provide new insight into the social and emotional deficits associated with PTSD and emphasize the importance of addressing the trauma histories and PTSD of both partners when treating veteran couples with relationship disturbance.

Attention-deficit/hyperactivity disorder comorbidity in a sample of veterans with posttraumatic stress disorder

This study examined attention-deficit/hyperactivity disorder (ADHD) comorbidity in military veterans with a high prevalence of posttraumatic stress disorder (PTSD) and evaluated the relationships between the 2 disorders and exposure to traumatic events. The sample included 222 male and female military veterans who were administered structured clinical interviews based on the Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition. Results show that 54.5% met the criteria for current PTSD, 11.5% of whom also met the criteria for current adult ADHD. Level of trauma exposure and ADHD severity were significant predictors of current PTSD severity. Evaluation of the underlying structure of symptoms of PTSD and ADHD using confirmatory factor analysis yielded a best-fitting measurement model that comprised 4 PTSD factors and 3 ADHD factors. Standardized estimates of the correlations among PTSD and ADHD factors suggested that the largest proportion of shared variance underlying PTSD-ADHD comorbidity is related to problems with modulating arousal levels that are common to both disorders (ie, hyperarousal and hypoarousal).

Associations between Pittsburgh Sleep Quality Index factors and health outcomes in women with posttraumatic stress disorder

OBJECTIVE The Pittsburgh Sleep Quality Index (PSQI) is a widely used measure of subjective sleep disturbance in clinical populations, including individuals with posttraumatic stress disorder (PTSD). Although the severity of sleep disturbance is generally represented by a global symptom score, recent factor analytic studies suggest that the PSQI is better characterized by a two- or three-factor model than a one-factor model. This study examined the replicability of two- and three-factor models of the PSQI, as well as the relationship between PSQI factors and health outcomes, in a female sample with PTSD. METHODS The PSQI was administered to 319 women with PTSD related to sexual or physical assault. Confirmatory factor analyses tested the relative fit of one-, two-, and three-factor solutions. Bivariate correlations were performed to examine the shared variance between PSQI sleep factors and measures of PTSD, depression, anger, and physical symptoms. RESULTS Confirmatory factor analyses supported a three-factor model with Sleep Efficiency, Perceived Sleep Quality, and Daily Disturbances as separate indices of sleep quality. The severity of symptoms represented by the PSQI factors was positively associated with the severity of PTSD, depression, and physical symptoms. However, these health outcomes correlated as much or more with the global PSQI score as with PSQI factor scores. CONCLUSIONS These results support the multidimensional structure of the PSQI. Despite this, the global PSQI score has as much or more explanatory power as individual PSQI factors in predicting health outcomes.

The contribution of childhood family violence on later intimate partner violence among robbery victims

This study examined the relative contributions of the three forms of childhood family violence exposure on physical intimate partner violence (IPV) victimization among recent robbery victims and tested a gender-matching modeling prediction for IPV risk. Data from a sample of 103 male and 93 female victims of a robbery were analyzed to investigate the effects of exposure to childhood physical abuse (CPA), childhood sexual abuse (CSA), and witnessing parental violence on the likelihood of IPV in adulthood. As expected, witnessing parental violence was associated with a 2.4-fold increase in IPV for both men and women. Neither CPA nor CSA was significantly associated with IPV after accounting for the effect of witnessing parental violence. There was support for the gender-matching hypothesis with men more likely to report IPV if they had witnessed mother-to-father violence and women more likely to report IPV if they had witnessed father-to-mother violence. Witnessing parental violence is strongly associated with risk for IPV victimization, particularly when the victim is the same-gender parent. Future directions and clinical implications are discussed.

Personality factors in resilience to traumatic stress

Introduction The study of individual differences in resilience to traumatic stress has received unprecedented attention in recent years from investigators in the field of post-traumatic stress disorder (PTSD) but there remains a lack of consensus regarding the definition, measurement, and conceptualization of the construct. Trait personality psychologists have grappled with similar issues since the seminal work of Jack Block (1961) on the construct of ego resilience over 50 years ago. In the process, they have developed comprehensive models of personality and psychometrically sophisticated tools for the measurement of its traits that can potentially inform and advance the study of resilience. The primary purpose of this chapter is to review the literature on personality factors involved in resilience to traumatic stress and to outline a model for conceptualizing this interface. Contemporary models of personality aim to identify the structure and basis for behavioral traits – defined as individual differences in patterns of thoughts, feelings, and actions that are consistent across developmental periods and environmental contexts. Personality models differ considerably with regard to the factor structure, number, and definition of specific traits. Because of this, research on personality traits that confer risk or resilience to the development of post-traumatic psychopathology has yielded a complicated collection of studies examining disparate constructs and measures. To provide coherence and organization to this literature, this chapter will focus on three broadband personality dimensions described by Tellegen (1985, 2000) that are also represented with subtle definitional variations in most other contemporary trait models of personality. For this reason, they are known as the “big three” personality factors: positive emotionality/extraversion (PEM), negative emotionality/neuroticism (NEM), and constraint/impulsivity (CON).

Psychometric Properties of the Schedule for Nonadaptive and Adaptive Personality in a PTSD Sample

This study evaluated the psychometric characteristics of the Schedule for Nonadaptive and Adaptive Personality (SNAP; Clark, 1996) in 280 individuals who screened positive for posttraumatic stress disorder (PTSD). The SNAP validity, trait, temperament, and personality disorder (PD) scales were compared with scales on the Brief Form of the Multidimensional Personality Questionnaire (Patrick, Curtin, & Tellegen, 2002). In a subsample of 86 veterans, the SNAP PD, trait, and temperament scales were also evaluated in comparison to the International Personality Disorder Examination (IPDE; Loranger, 1999), a semistructured diagnostic interview. Results revealed that the SNAP scales have good convergent validity, as evidenced by their pattern of associations with related measures of personality and PD. However, evidence for their discriminant validity in relationship to other measures of personality and PD was more mixed, and test scores on the SNAP trait and temperament scales left much unexplained variance in IPDE-assessed PDs. The diagnostic scoring of the SNAP PD scales greatly inflated prevalence estimates of PDs relative to the IPDE and showed poor agreement with the IPDE. In contrast, the dimensional SNAP scores yielded far stronger associations with continuous scores on the IPDE. The SNAP scales also largely evidenced expected patterns of association with a measure of PTSD severity. Overall, findings support the use of this measure in this population and contribute to our conceptualization of the association between temperament, PTSD, and Axis II psychopathology.

Design and conduct of a provider survey to determine a clinically persuasive effect size in planning VA Cooperative Study #590 (Li+)

Background The estimation of an effect size is an important step in designing an adequately powered, feasible clinical trial intended to change clinical practice. During the planning phase of VA Cooperative Study #590, “Double-Blind Placebo-Controlled Study of Lithium for Preventing Repeated Suicidal Self-Directed Violence in Patients with Depression or Bipolar Disorder (Li+),” it was not clear what effect size would be considered large enough to influence prescribing behavior among practicing clinicians. Methods We conducted an online survey of VA psychiatrists to assess their interest in the study question, their clinical experience with lithium, and their opinion about what suicide reduction rate would change their prescribing habits. The 9-item survey was hosted on SurveyMonkey© and VA psychiatrists were individually emailed an invitation to complete an anonymous online survey. Three email waves were sent over three weeks. Results Overall, 862 of 2713 VA psychiatrists (response rate = 31.8%) responded to the anonymous survey. 74% of the respondents would refer a patient to the proposed trial, 9% would not, and 17% were unsure. Presented with suicide reduction rates in 10% increments ranging from 10 to 100%, 61% of respondents indicated that they would use lithium if suicide attempts were reduced by at least 40%; 83% would use lithium if it reduced attempts by at least 50%. Conclusions Even with the limitations of response bias and the reliability of responses on future prescribing behavior, a survey of potential users of a clinical trials results offers a convenient, empirical method for determining and justifying clinically relevant effect sizes.