Do Social Support and Loneliness Influence Emerging Adults' Mental Health during the First Year of the COVID-19 Pandemic?

Youths' mental health is at a crisis level, with mental health problems doubling in the US since the pandemic began. To compound the mental health crisis, there is a global loneliness epidemic, with emerging adults worldwide experiencing some of the highest rates. One study with two phases examined the influence of social support and loneliness on mental health in US emerging adults during the pandemic, including changes in these relationships over one year. Emerging adults (N = 449) completed online questionnaires via Prolific in May 2020 (Phase 1) and again from January to May 2021 (N = 253; Phase 2). More perceived support was related to reduced loneliness, with family support having the most significant influence. Loneliness mediated the link between perceived support and adverse health outcomes. Higher loneliness predicted more perceived stress and sleep difficulties concurrently and over time. There was a bidirectional relationship between loneliness and depression, such that higher levels of either variable at Time 1 predicted increases in the other over time. Results highlight the detrimental impact of loneliness on emerging adults' mental health.

Emotional Distress in a Marginalized Population as a Function of Household-Level Social Determinants of Health

Low-income, underrepresented communities of color are disproportionally affected by emotional distress. Little is known about malleable, household-level determinants of emotional distress, addressable by feasible, stigma-neutral interventions. The present study addressed this knowledge gap by analyzing secondary data from a cross-sectional community needs assessment survey in a marginalized urban community (N = 677). Relying on dominance analyses, authors found that, on average, the largest household-level contributions to respondents' emotional distress included exposures to fellow household members' alcohol use and anger-driven behaviors. Both determinants are arguably feasible to address via household-level interventions and community-level preventive efforts. Household members' physical and serious mental illness and drug use were moderately associated with respondents' emotional distress; household cohesion and communications, residential overcrowding, and child behavior played a minimal role. Article concludes with a discussion of public health implications of the results.

Differences among factors associated with tobacco product use among Black and White adolescents: A cross-sectional analysis of wave one of the PATH study 2013-2014

INTRODUCTION

Tobacco use remains a primary cause of health disparities between Black and White Americans. Current approaches have not improved tobacco-related racial health disparities. This study aimed to identify differences in factors associated with tobacco product use among Black and White adolescents.

METHODS

This cross-sectional design used data from Wave One (2013-2014) of the Population Assessment of Tobacco and Health Study. Adolescents aged 12-17 years who identified as non-Hispanic Black or African American (n=1800) or non-Hispanic White (n=6495) were included. Primary outcomes were the ever use and current use of any tobacco products. Sociocultural, household environment, psychological, and behavioral factors were included. Logistic regressions, stratified by race, were used to determine significance. Dominance analysis was used to rank significant factors by their level of importance.

RESULTS

Although there were many Black-White commonalities, there were also important differences. Black adolescents in the Northeast were more likely to have ever used tobacco compared to those in the South (OR=0.6; 95% CI: 0.6-0.7, p<0.001) and Midwest (OR=0.6; 95% CI: 0.5-0.7, p<0.001). White adolescents in the Northeast were less likely to use tobacco products than in other regions. Peer influences (OR=1.9; 95% CI: 1.1-3.2, p<0.05) were uniquely associated with ever use among Black adolescents. Access to tobacco in the home (OR=2.0; 95% CI: 1.4-3.0, p<0.001) and thinking that tobacco use would help reduce stress (OR=1.3; 95% CI: 1.1-1.6, p<0.01) were uniquely associated with current use among Black adolescents.

CONCLUSIONS

There are significant Black-White differences in the factors associated with tobacco use. Factors uniquely associated with Black adolescent tobacco use should be considered in developing strategies to prevent adolescent tobacco use in Black communities.

Workplace mistreatment and insomnia: a prospective study of child welfare workers

OBJECTIVE

This study examines how workplace mistreatment relates to insomnia among child welfare workers. The main aim was to determine the impact of three different forms of mistreatment, namely client perpetrated violence, cyber harassment, and colleague perpetrated bullying, on changes in levels of insomnia over time. A secondary aim was to examine whether these three forms of mistreatment represent overlapping or distinct and unique phenomena.

METHODS

The study was based on a probability sampled prospective survey of 424 Norwegian child welfare workers. Time lag between baseline and follow-up was six months. A confirmatory factor analysis determined the dimensionality of the indicators of mistreatment. TwoStep cluster analysis was used to examine patterns of exposure. Between and within group changes in insomnia was determined with linear regression analyses and repeated measures ANOVA. Dominance analysis was used to investigate the relative impact the predictor variables had on insomnia.

RESULTS

Client perpetrated violence and colleague perpetrated bullying were associated with increased levels of insomnia over time. Exposure to bullying was established as the most prominent predictor. Client perpetrated violence, cyber harassment, and colleague perpetrated bullying represent unique and distinct constructs. Child welfare workers mainly report exposure to one form of mistreatment rather than a combination of different types.

CONCLUSIONS

Client perpetrated violence and colleague perpetrated bullying were established as risk factors for insomnia among child welfare workers. Employers and human resource personnel should prioritize developing effective primary, secondary, and tertiary strategies to prevent and handle these hazards and thereby reduce the risk of insomnia among workers.

Interannual Variability of Summer Hotness in China: Synergistic Effect of Frequency and Intensity of High Temperature

In the context of global warming, the impact of summer high temperature events is increasing. The accumulated summer high temperature is often used to reflect the overall hotness of summer. The internal variation of the accumulated temperature can be affected by both the frequency and intensity. In this study, by using the daily data during summers of 1960–2018, we examine the relative importance of the two factors with a multiple linear regression method. It is demonstrated that that the dominant result of summer accumulated temperature is sensitive to the change of threshold. As the threshold increases, the importance of frequency gradually increases, while the importance of the intensity decreases. In addition, it is found that when the threshold changes, the sensitivity of the dominant results is different over regions. This can provide a basis for the selection of regional thresholds and further improve the representation of accumulated temperature for high summer temperatures.

Global hippocampal and selective thalamic nuclei atrophy differentiate chronic TBI from Non-TBI

Traumatic brain injury (TBI) may increase susceptibility to neurodegenerative diseases later in life. One neurobiological parallel between chronic TBI and neurodegeneration may be accelerated aging and the nature of atrophy across subcortical gray matter structures. The main aim of the present investigation is to evaluate and rank the degree that subcortical gray matter atrophy differentiates chronic moderate-severe TBI from non-TBI participants by evaluating morphometric differences between groups. Forty individuals with moderate-severe chronic TBI (9.23 yrs from injury) and 33 healthy controls (HC) underwent high resolution 3D T1-weighted structural magnetic resonance imaging. Whole brain volume was classified into white matter, cortical and subcortical gray matter structures with hippocampi and thalami further segmented into subfields and nuclei, respectively. Extensive atrophy was observed across nearly all brain regions for chronic TBI participants. A series of multivariate logistic regression models identified subcortical gray matter structures of the hippocampus and thalamus as the most sensitive to differentiating chronic TBI from non-TBI participants (McFadden R² = .36, p < .001). Further analyses revealed the pattern of hippocampal atrophy to be global, occurring across nearly all subfields. The pattern of thalamic atrophy appeared to be much more selective and non-uniform, with largest between-group differences evident for nuclei bordering the ventricles. Subcortical gray matter was negatively correlated with time since injury (r = -.31, p = .054), while white matter and cortical gray matter were not. Cognitive ability was lower in the chronic TBI group (Cohen's d = .97, p = .003) and correlated with subcortical structures including the pallidum (r² = .23, p = .038), thalamus (r² = .36, p = .007) and ventral diencephalon (r² = .23, p = .036). These data may support an accelerated aging hypothesis in chronic moderate-severe TBI that coincides with a similar neuropathological profile found in neurodegenerative diseases.

Bayesian Sensitivity-Specificity and ROC Analysis for Finding Key Drivers

Finding key drivers in regression modeling via Bayesian Sensitivity-Specificity and Receiver Operating Characteristic is suggested, and clearly interpretable results are obtained. Numerical comparisons with other techniques show that this methodology can be useful in practical statistical modeling and analysis helping to researchers and managers in making meaningful decisions.

The Differential Importance of Component Skills on Reading Comprehension Test Performance Among Struggling Adolescent Readers

Reading comprehension tests vary in format and characteristics, which may influence the extent to which component skills are involved in test performance. With students in Grades 6 to 8 with reading difficulties, dominance analyses examined the differential importance of component reading and language skills (word- and text-reading fluency, vocabulary, listening comprehension, and working memory) on several standardized tests of reading comprehension: The Gates-MacGinitie Reading Test, 4th edition (GMRT), Group Reading Assessment and Diagnostic Evaluation, Gray Oral Reading Test, 5th edition (GORT-5), and the Test of Silent Reading Efficiency and Comprehension (TOSREC). Students' word- and text-reading fluency skills were generally the most dominant predictors of performance on most reading comprehension tests, especially those with a time limit (GMRT and TOSREC). Listening comprehension was most important on the GORT-5, a test in which students read passages orally and listen to questions read by an examiner. Working memory was the least important component skill across the reading comprehension tests. Overall, results were consistent with previous work indicating that reading comprehension measures vary with regard to the skills or knowledge sources that are most important for test performance and extend these findings to struggling adolescent readers. Implications for research and practice are discussed.

Risk Factors for Development of Acute Kidney Injury in COVID-19 Patients: A Retrospective Observational Cohort Study

INTRODUCTION

Acute kidney injury (AKI) in coronavirus infection disease (COVID-19) is associated with disease severity. We aimed to evaluate risk factors associated with AKI beyond COVID-19 severity.

METHODS

A retrospective observational study of COVID-19 patients admitted to a tertiary hospital in Singapore. Logistic regression was used to evaluate associations between risk factors and AKI (based on Kidney Disease Improving Global Outcomes criteria). Dominance analysis was performed to evaluate the relative importance of individual factors.

RESULTS

Seven hundred seven patients were included. Median age was 46 years (interquartile range [IQR]: 29-57) and 57% were male with few comorbidities (93%, Charlson Comorbidity Index [CCI] <1). AKI occurred in 57 patients (8.1%); 39 were in AKI stage 1 (68%), 9 in stage 2 (16%), and 9 in stage 3 (16%). Older age (adjusted odds ratio [aOR] 1.04; 95% confidence interval [CI]: 1.01-1.07), baseline use of angiotensin-converting enzyme inhibitor (ACE-I) or angiotensin receptor blocker (ARB) (aOR 2.86; 95% CI: 1.20-6.83), exposure to vancomycin (aOR 5.84; 95% CI: 2.10-16.19), use of nonsteroidal anti-inflammatory drugs (NSAIDs) (aOR 3.04; 95% CI: 1.15-8.05), and severe COVID-19 with hypoxia (aOR 13.94; 95% CI: 6.07-31.98) were associated with AKI in the multivariable logistic regression model. The 3 highest ranked predictors were severe COVID-19 with hypoxia, vancomycin exposure, and age, accounting for 79.6% of the predicted variance (41.6, 23.1, and 14.9%, respectively) on dominance analysis.

CONCLUSION

Severe COVID-19 is independently associated with increased risk of AKI beyond premorbid conditions and age. Appropriate avoidance of vancomycin and NSAIDs are potentially modifiable means to prevent AKI in patients with COVID-19.

Body Dysmorphic Disorder in the Perspective of the Alternative DSM-5 Model for Personality Disorder: A Study on Italian Community-Dwelling Women

To evaluate the relationships between body dysmorphic disorder (BDD) and Alternative DSM-5 Model for Personality Disorder (AMPD) criterion A and dysfunctional personality trait (i.e., criterion B) measures, 420 Italian community-dwelling women were administered three measures of BDD (i.e., the Body Dysmorphic Disorder Questionnaire, the Body Dysmorphic Disorder-Dimensional Scale, and the Appearance Anxiety Inventory), as well as the Level of Personality Functioning Scale-Brief Form (LPFS-BF) and the Personality Inventory for DSM-5-Short Form (PID-5-SF). The three BDD measures showed substantial convergent validity correlations and could be reliably cumulated to obtain the BDD Cumulative Index (BDDCI). Several significant, nonnegligible correlations were observed between the BDDCI as well as the LPFS-BF scale scores and PID-5-SF personality trait scale scores. Relative importance weight analysis results showed that LPFS-BF scale scores and PID-5-SF trait scale scores were substantial predictors of the BDDCI scores (R = 0.42, f = 0.72). In particular, AMPD criterion A impairment in self-functioning and AMPD criterion B depressivity, anhedonia, perseveration, separation insecurity, and cognitive and perceptual dysregulation were core components of the dysfunctional personality profile associated with BDD.

The role of staffing and classroom characteristics on preschool teachers' use of one-to-one intervention with children with autism

LAY ABSTRACT

For preschool children with autism, individual (one-to-one) behavioral interventions are among the best-tested treatments. However, they are rarely used in special education preschools. We observed formally and informally delivered one-to-one behavioral interventions use by classroom staff (n = 51) in 12 classrooms across three special education preschools for children with autism, aged 3-6 years, in a major US city. We estimated the associations between one-to-one intervention use and classroom characteristics including staff-student ratio, professional role composition, and frequency of challenging child behaviors. As a whole, the factors we examined were considerably important for both formally and informally delivered one-to-one interventions. The number of individually assigned personal care aides in the classroom was negatively associated with the use of formally delivered one-to-one intervention. Classroom challenging behavior was positively associated with use of formally delivered one-to-one interventions. Interventionist's professional roles and the number of children in the class were most important for the use of informally delivered interventions. Staff training, clarifying professional roles, setting performance expectations for personal care aides and other classroom team members, and reducing class size may represent promising implementation targets. Findings suggest caution around task-shifting policies that transfer clinical functions from more highly trained to less highly trained staff.

What Motivates Mental Health Clinicians-in-Training to Implement Evidence-Based Assessment? A Survey of Social Work Trainees

Mental health clinicians do not consistently use evidence-based assessment (EBA), a critical component of accurate case conceptualization and treatment planning. The present study used the Unified Theory of Behavior to examine determinants of intentions to use EBA in clinical practice among a sample of Masters' level social work trainees (N = 241). Social norms had the largest effect on intentions to use EBA. Injunctive norms in reference to respected colleagues accounted for the most variance in EBA intentions. Findings differed for respondents over 29 years of age versus younger respondents. Implications for implementation strategies and further research are discussed.

Relative importance of caregiver characteristics for future alcohol consumption in youth involved with child welfare system

BACKGROUND

Adolescents involved with child welfare system are disproportionately at risk for underage drinking. Little empirical evidence has informed interventions targeting child welfare caregivers to prevent alcohol consumption among adolescents involved with the system.

METHODS

The present study addressed this gap by examining modifiable caregiver characteristics most predictive of future underage drinking in a cohort of adolescents (N = 1205) in a nationally representative child welfare dataset. We used dominance analyses to examine direct contributions of each caregiver predictor to the overall variance of future alcohol use. This is the first study to apply the reputable Turrisi and Jaccard (2001) framework of familial processes affecting underage drinking to the child welfare population.

RESULTS

Findings highlight the role of caregiver-adolescent relational quality and communications for predicting underage alcohol use, and downplay the role of caregiver monitoring.

CONCLUSIONS

Child welfare service systems may help prevent underage drinking by systematically training and motivating caregivers to foster trusting, helping relationships and regular communications with the adolescents in their care.

Important Considerations When Selecting a Risk Assessment Tool

Measurement is an integral part of many disciplines, ranging from the social, healthcare/medical, to management sciences. The field of psychometrics has had a wide-ranging impact in the varied disciplines housed within psychology (e.g., clinical, developmental, etc.) as researchers and test developers aim to construct, refine, and modify their instruments. Given that test validation is a key component in furnishing evidence of validity, the intent of this nontechnical article is to reinforce (or serve as a reminder) for the applied audience the necessary efforts in optimizing the psychometric properties of their measurement tool. This article will be couched as a "lessons learned" document, primarily covering construct and criterion validity, but also, reliability estimation, and then finally, a comment about the confluence of null hypothesis significance testing, sample size and effect size and its relationship to psychometric testing.

Energy intensity modeling for wastewater treatment technologies

Wastewater treatment plants (WWTPs) are energy intensive facilities; therefore increased pressure has been placed on managers and policy makers to reduce the facilities' energy use. Several studies were conducted to compare the energy intensity (EI) of WWTPs, which showed large dispersion in EI among the facilities. In the present study, the degree EI influenced WWTPs was tested using a set of technical variables by modeling the EI of a 305 WWTP sample grouped into five secondary treatment technologies. Results indicated the following two major findings: i) WWTPs using conventional activated sludge, extended aeration, trickling biofilters, and biodisks exhibited significant economies of scale in energy use; and ii) pollutant removal efficiency demonstrated low impacts on WWTP EI. The methodology and results of this study are of value to policy makers in planning new WWTPs and developing management plans to improve energy efficiency of wastewater treatment.

It's more than skin-deep: The relationship between social victimization and telomere length in adolescence

This study examined the relationship between peer victimization and telomere length (TL), an indicator of biological aging that is associated with stressors (Epel, 2009). It was predicted that social victimization would have a greater impact upon TL, as well as the frequency and severity of health complaints than physical victimization. Adolescents (M_age  = 15.91 years, SD_age  = 1.65) and their parents completed measures of peer victimization and physical health problems; adolescents also submitted a DNA sample for telomere analysis. Greater instances of being socially, but not physically, victimized were associated with shorter telomeres, as well as more frequent and severe health complaints. TL was also negatively related to both the frequency and severity of health problems, even after controlling for BMI, age, and sex of participant. The relationship between social victimization and health complaints via TL held only at higher levels of social victimization. These findings are the first to find an association between peer victimization and shortened telomeres.

Using Dominance Analysis to Decompose Narcissism and Its Relation to Aggression and Externalizing Outcomes

Research on narcissism has shown it to be multidimensional construct. As such, the relations the larger construct bear with certain outcomes may mask heterogeneity apparent at the more basic trait level. This article used the Five Factor Narcissism Inventory, a Five-Factor Model-based measure of narcissism that allows for multiple levels of analysis, to examine the relative importance of narcissistic traits in relation to aggression, externalizing behavior, and self-esteem outcomes in two independent samples. The relative importance of the narcissism factors was determined through the use of dominance analysis-a relatively underused method for determining relative importance among a set of related predictors. The results showed that antagonism, compared with agentic extraversion and neuroticism, was the dominant predictor across all forms of aggressive behavior. Additional analyses showed that subscales within the broader factor of antagonism also showed differential importance relative to one another for certain aggression outcomes. The results are discussed in the context of the relation between narcissism and aggression and highlight the utility of using extensions of regression-based analyses to explore the heterogeneity within personality constructs.

Evaluating predictors of dispersion: a comparison of Dominance Analysis and Bayesian Model Averaging

Conventional measures of predictor importance in linear models are applicable only when the assumption of homoscedasticity is satisfied. Moreover, they cannot be adapted to evaluating predictor importance in models of heteroscedasticity (i.e., dispersion), an issue that seems not to have been systematically addressed in the literature. We compare two suitable approaches, Dominance Analysis (DA) and Bayesian Model Averaging (BMA), for simultaneously evaluating predictor importance in models of location and dispersion. We apply them to the beta general linear model as a test-case, illustrating this with an example using real data. Simulations using several different model structures, sample sizes, and degrees of multicollinearity suggest that both DA and BMA largely agree on the relative importance of predictors of the mean, but differ when ranking predictors of dispersion. The main implication of these findings for researchers is that the choice between DA and BMA is most important when they wish to evaluate the importance of predictors of dispersion.

Relative Importance Analysis With Multicategory Dependent Variables:

Determining independent variable relative importance is a highly useful practice in organizational science. Whereas techniques to determine independent variable importance are available for normally distributed and binary dependent variable models, such techniques have not been extended to multicategory dependent variables (MCDVs). The current work extends previous research on binary dependent variable relative importance analysis to provide a methodology for conducting relative importance analysis on MCDV models from a dominance analysis (DA) perspective. Moreover, the current work provides a set of comprehensive data analytic examples that demonstrate how and when to use MCDV models in a DA and the advantages general DA statistics offer in interpreting MCDV model results. Moreover, the current work outlines best practices for determining independent variable relative importance for MCDVs using replicable examples on data from the publicly available General Social Survey. The present work then contributes to the literature by using in-depth data analytic examples to outline best practices in conducting relative importance analysis for MCDV models and by highlighting unique information DA results provide about MCDV models.

On Johnson's (2000) Relative Weights Method for Assessing Variable Importance: A Reanalysis

This article provides a reanalysis of J. W. Johnson's (2000) "relative weights" method for assessing variable importance in multiple regression. The primary conclusion of the reanalysis is that the derivation of the method is theoretically flawed and has no more validity than the discredited method of Green, Carroll, and DeSarbo (1978) on which it is based. By means of 2 examples, supplemented by other results from the literature, it is also shown that the method can result in materially distorted inferences when it is compared with another widely used importance metric, namely, general dominance (Azen & Budescu, 2003; Budescu, 1993). Our primary recommendation is that J. W. Johnson's (2000) relative weights method should no longer be used as a variable importance metric for multiple linear regression. In the final section of the article, 2 additional recommendations are made based on our analysis, examples, and discussion.

Understanding the Results of Multiple Linear Regression

Multiple linear regression (MLR) remains a mainstay analysis in organizational research, yet intercorrelations between predictors (multicollinearity) undermine the interpretation of MLR weights in terms of predictor contributions to the criterion. Alternative indices include validity coefficients, structure coefficients, product measures, relative weights, all-possible-subsets regression, dominance weights, and commonality coefficients. This article reviews these indices, and uniquely, it offers freely available software that (a) computes and compares all of these indices with one another, (b) computes associated bootstrapped confidence intervals, and (c) does so for any number of predictors so long as the correlation matrix is positive definite. Other available software is limited in all of these respects. We invite researchers to use this software to increase their insights when applying MLR to a data set. Avenues for future research and application are discussed.

Residualized Relative Importance Analysis

The current article notes that the standard application of relative importance analyses is not appropriate when examining the relative importance of interactive or other higher order effects (e.g., quadratic, cubic). Although there is a growing demand for strategies that could be used to decompose the predicted variance in regression models containing such effects, there has been no formal, systematic discussion of whether it is appropriate to use relative importance statistics in such decompositions, and if it is appropriate, how to go about doing so. The purpose of this article is to address this gap in the literature by describing three different yet related strategies for decomposing variance in higher-order multiple regression models—hierarchical F tests (a between-sets test), constrained relative importance analysis (a within-sets test), and residualized relative importance analysis (a between- and within-sets test). Using a previously published data set, we illustrate the different types of inferences these three strategies permit researchers to draw. We conclude with recommendations for researchers seeking to decompose the predicted variance in regression models testing higher order effects.

Exploratory regression analysis: a tool for selecting models and determining predictor importance

Linear regression analysis is one of the most important tools in a researcher's toolbox for creating and testing predictive models. Although linear regression analysis indicates how strongly a set of predictor variables, taken together, will predict a relevant criterion (i.e., the multiple R), the analysis cannot indicate which predictors are the most important. Although there is no definitive or unambiguous method for establishing predictor variable importance, there are several accepted methods. This article reviews those methods for establishing predictor importance and provides a program (in Excel) for implementing them (available for direct download at http://dl.dropbox.com/u/2480715/ERA.xlsm?dl=1) . The program investigates all 2(p) - 1 submodels and produces several indices of predictor importance. This exploratory approach to linear regression, similar to other exploratory data analysis techniques, has the potential to yield both theoretical and practical benefits.

Relationships between psychological safety climate facets and safety behavior in the rail industry: a dominance analysis

The goals of this study were twofold: (1) to confirm a relationship between employee perceptions of psychological safety climate and safety behavior for a sample of workers in the rail industry and (2) to explore the relative strengths of relationships between specific facets of safety climate and safety behavior. Non-management rail maintenance workers employed by a large North American railroad completed a survey (n=421) regarding workplace safety perceptions and behaviors. Three facets of safety climate (management safety, coworker safety, and work-safety tension) were assessed as relating to individual workers' reported safety behavior. All three facets were significantly associated with safety behavior. Dominance analysis was used to assess the relative importance of each facet as related to the outcome, and work-safety tension evidenced the strongest relationship with safety behavior.

In Harm's Way: Factors Related to Psychological Distress Following Sexual Harassment

The negative consequences for victims of sexual harassment are well documented. However, one area unexamined is the process that leads to harm. Researchers have proposed three influences (i.e., objective or stimulus factors, individual factors, and contextual factors) on the psychological, health-related, and organizational outcomes of sexual harassment. This article examines the relative contribution of these influences on psychological distress following sexual harassment. Two studies were conducted. First, we examined approximately 1,200 women in a financial industry class-action lawsuit. A series of hierarchical regressions and subsequent dominance analysis revealed that the severity of the experiences and attributions made about them were the most important influences on symptoms of psychological distress. Study 2 examined 85 female plaintiffs in sexual harassment litigation. Dominance analysis again showed that the magnitude of their experiences had the strongest relationship with distress. Implications of these findings are discussed.

Determining the Relative Importance of Predictors in Logistic Regression: An Extension of Relative Weight Analysis

Techniques such as dominance analysis and relative weight analysis have been proposed recently to evaluate more accurately predictor importance in ordinary least squares (OLS) regression. Similar questions of predictor importance also arise in instances where logistic regression is the primary mode of analysis. This article presents an extension of relative weight analysis that can be applied in logistic regression and thus aids in the determination of predictor importance. We briefly review relative importance techniques and then discuss a new procedure for calculating relative importance estimates in logistic regression. Finally, we present a substantive example applying this new approach to an example data set.

Comparing the squared multiple correlation coefficients of non-nested models: an examination of confidence intervals and hypothesis testing

The performance of the asymptotic method for comparing the squared multiple correlations of non-nested models was investigated. Specifically, the increase in a given regression model's R2 when one predictor is added was compared to the increase in the same model's R2 when another predictor is added. This comparison can be used to determine predictor importance and is the basis for procedures such as Dominance Analysis. Results indicate that the asymptotic procedure provides the expected coverage rates for sample sizes of 200 or more, but in many cases much higher sample sizes are required to achieve adequate power. Guidelines and computations are provided for the determination of adequate sample sizes for hypothesis testing.