Search

Missing data in longitudinal randomized clinical trials, even if assumed to be missing at random (MAR), can result in biased parameter estimates and incorrect treatment conclusions. If missing data are suspected to be missing not at random (MNAR, i.e., missing data due to the unobserved values themselves), accepted missing data handling techniques are inadequate and the problem is compounded due to the introduction of additional bias. The goal of this paper is to provide trialists the analytic tools and methodological steps needed to assess treatment effect veracity if MNAR is suspected, enabling researchers to reach reasonable and defensible treatment effect conclusions. The explanations, steps, and conclusions are demonstrated using trial data involving binge drinking behavior among college students. All analysis model diagrams are presented, and both linear model equations and Mplus syntax scripts for all analyses are included in a supplemental Appendix to further provide trialists the methodological tools needed to further test treatment effect estimates when MNAR is suspected.

Juvenile fibromyalgia (JFM) is a chronic condition characterized by symptoms of pain and fatigue and is associated with sedentary behavior and functional disability. Adults with fibromyalgia exhibit deficits in physical fitness as evidenced by lower aerobic capacity and physical endurance, but it is unknown whether these impairments are apparent in adolescents with JFM. Furthermore, the extent to which functional disability and pain interference relate to measures of physical fitness has not been investigated in a pediatric pain population. During a baseline assessment for a clinical trial, 321 adolescents with juvenile fibromyalgia (Mage = 15.14, 85.2% female) completed measures of pain intensity, fatigue, JFM symptom severity, functional disability, and pain interference. They also completed 2 validated fitness tasks: (1) the Harvard step test, which assesses aerobic fitness, and (2) the 6-minute walk test, a simple submaximal test of endurance. We examined associations among self-report measures and fitness assessments using bivariate correlations. We then employed hierarchical regression analyses to determine the unique contributions of physical fitness assessments to self-reported functional disability and pain interference. Results indicated that youth with JFM exhibited deficits in aerobic capacity and physical endurance. However, physical fitness explained negligible variance in functional disability and pain interference beyond that accounted for by pain, fatigue, and JFM symptom severity. Scores on available functional disability measures may reflect perceived difficulties in coping with symptoms during physical tasks rather than actual physical capability. Rigorous and sensitive assessments of physical fitness and endurance are needed to determine whether rehabilitation interventions for pediatric pain improve physical functioning. [ABSTRACT FROM AUTHOR]

Cognitive disengagement syndrome (CDS), previously termed sluggish cognitive tempo (SCT), is characterized by excessive daydreaming, mental confusion, and slowed behavior or thinking. Prior research has found inconsistent relations between CDS and neurocognition, though most studies have used small or ADHD-defined samples, non-optimal measures of CDS, and/or examined limited neurocognitive domains. Accordingly, this study examined the association of parent- and teacher-reported CDS symptoms using a comprehensive neurocognitive battery in a sample of 263 children (aged 8–12) selected with a range of CDS symptomatology. Parents and teachers provided ratings of CDS and ADHD inattentive (ADHD-IN) symptoms. Path analyses were conducted to examine CDS and ADHD-IN as unique predictors of neurocognitive functioning after covarying for age, sex, and family income. CDS symptoms were uniquely associated with slower performance across a range of cognitive domains, including verbal inhibition, rapid naming/reading, planning, divided attention, and set shifting. In contrast, ADHD-IN symptoms were uniquely associated with poorer performance on a Go/NoGo task (inhibition/distractibility), visual scanning and discrimination, and interference control. Findings from the current study, amongst the first to recruit children based on levels of CDS symptomatology, provide the strongest evidence to date that the neurocognitive phenotype of CDS is characterized by slowed cognitive processing, and add to its validity as a separate syndrome from ADHD. If replicated, these findings have implications for assessment, treatment, and school accommodations for CDS. Neuroimaging studies exploring the neurobiological basis of CDS are also needed. [ABSTRACT FROM AUTHOR]

Researchers in the field of early adolescence interested in quantifying the environmental influences on a response variable of interest over time would use cluster sampling (i.e., obtaining repeated measures from students nested within classrooms and/or schools) to obtain the needed sample size. The resulting longitudinal data would be nested at three levels (e.g., repeated measures [Level 1], collected across participants [Level 2], and nested within different schools [Level 3]). A previous publication addressed statistical analysis issues specific to cross-sectional three-level data analytic designs. This article expands upon the previous cross-sectional three-level publication to address topics specific to longitudinal three-level data analyses efforts. Although all analysis examples are demonstrated using SAS, the equivalent SPSS and Mplus syntax scripts, as well as the generated example data and additional supplemental materials, are available online.

Background: Youth with continuous (always present) headache are vastly understudied; much remains to be understood regarding treatment response in this population. Objective: To describe and explore biopsychosocial factors related to initial clinical outcomes among treatment‐seeking youth with continuous headache. Methods: This retrospective cohort study extracted data of 782 pediatric patients (i.e., aged <18 years) with continuous headache from a large clinical repository. Youth in this study had experienced continuous headache for ≥1 month before presenting to a multidisciplinary headache specialty clinic appointment. Extracted data from this appointment included patients' headache history, clinical diagnoses, and headache‐related disability, as well as information about biopsychosocial factors implicated in headache management and/or maintenance (e.g., healthy lifestyle habits, history of feeling anxious or depressed). Additional data regarding patient headache characteristics, disability, and lifestyle habits were extracted from a subset of 529 youth who returned to clinic 4–16 weeks after their initial follow‐up visit. After characterizing initial treatment response, exploratory analyses compared youth with the best and worst treatment outcomes on several potentially influential factors. Results: Approximately half of youth (280/526; 53.2%) continued to have continuous headache at follow‐up, ~20% of youth (51/526) reported a significant (≥50%) reduction in headache frequency. Improvements in average headache severity (e.g., percentage with severe headaches at initial visit: 45.3% [354/771]; percentage with severe headaches at follow‐up visit: 29.8% [156/524]) and headache‐related disability were also observed (e.g., percentage severe disability at initial visit: 62.9% [490/779]; percentage severe disability at initial follow‐up visit: 34.2% [181/529]). Individuals with the worst headache frequency and disability had a longer history of continuous headache (mean difference estimate = 5.76, p = 0.013) and worse initial disability than the best responders (χ2[3, 264] = 23.49, p < 0.001). They were also more likely to have new daily persistent headache (χ2[2, 264] = 12.61, p = 0.002), and were more likely to endorse feeling depressed (χ2[1, 260] = 11.46, p < 0.001). Conclusion: A notable percentage of youth with continuous headache show initial improvements in headache status. Prospective, longitudinal research is needed to rigorously examine factors associated with continuous headache treatment response. [ABSTRACT FROM AUTHOR]

Applied early adolescent researchers often sample students (Level 1) from within classrooms (Level 2) that are nested within schools (Level 3), resulting in data that requires multilevel modeling analysis to avoid Type 1 errors. Although several articles have been published to assist researchers with analyzing sample data nested at two levels, few articles are available to researchers seeking assistance with three-level data analyses. The purpose of this article is to extend the presentational logic and pedagogical flow employed in previous two-level pedagogical publications to illustrate the relevant issues researchers face, the decisions to be made, and the proper procedures needed, when analyzing cross-sectional three-level data. These procedures are demonstrated with a generated three-level data example based on the Early Childhood Longitudinal Study (ECLS-K) public use dataset. The generated data used in this article, as well as the SPSS, SAS, and Mplus model specification syntax files needed to reproduce all analyses in this article, and additional illustrative examples, are available as supplemental online materials at http://jea.sagepub.com/content/early/recent.

Mixed-dyadic data, collected from distinguishable (nonexchangeable) or indistinguishable (exchangeable) dyads, require statistical analysis techniques that model the variation within dyads and between dyads appropriately. The purpose of this article is to provide a tutorial for performing structural equation modeling analyses of cross-sectional and longitudinal models for mixed independent variable dyadic data, and to clarify questions regarding various dyadic data analysis specifications that have not been addressed elsewhere. Artificially generated data similar to the Newlywed Project and the Swedish Adoption Twin Study on Aging were used to illustrate analysis models for distinguishable and indistinguishable dyads, respectively. Due to their widespread use among applied researchers, the AMOS and M"plus" statistical analysis software packages were used to analyze the dyadic data structural equation models illustrated here. These analysis models are presented in sufficient detail to allow researchers to perform these analyses using their preferred statistical analysis software package. (Contains 11 figures, 4 tables, and 6 footnotes.)

Home visiting is a child abuse prevention strategy that seeks to optimize child development by providing mothers with support, training, and parenting information. Research has consistently found high rates of depression in mothers participating in home visiting programs and low levels of obtaining mental health treatment in the community. Successful treatment of depressed mothers in home visiting programs holds the potential to improve maternal and child outcomes. In-Home Cognitive-Behavioral Therapy (IH-CBT) is an adapted treatment for depressed mothers, which is provided alongside home visiting and seeks to optimize engagement and impact through delivery in the home setting; a focus on issues important to young, low-income mothers; and a strong collaborative relationship between therapists and home visitors. This study examined predictors of depression status at posttreatment in 60 mothers who received IH-CBT and concurrent home visiting. Variables considered included demographics, illness history, severity, and numbers of treatment sessions and home visits. Results indicated that young maternal age, fewer episodes of major depressive disorder, lower depression severity at pretreatment, lower levels of symptoms of personality disorders, and more treatment sessions and home visits predicted asymptomatic status at posttreatment. (Contains 3 tables and 1 figure.)

Collecting data from students within classrooms or schools, and collecting data from students on multiple occasions over time, are two common sampling methods used in educational research that often require multilevel modeling (MLM) data analysis techniques to avoid Type-1 errors. The purpose of this article is to clarify the seven major steps involved in a multilevel analysis: (1) clarifying the research question, (2) choosing the appropriate parameter estimator, (3) assessing the need for MLM, (4) building the level-1 model, (5) building the level-2 model, (6) multilevel effect size reporting, and (7) likelihood ratio model testing. The seven steps are illustrated with both a cross-sectional and a longitudinal MLM example from the National Educational Longitudinal Study (NELS) dataset. The goal of this article is to assist applied researchers in conducting and interpreting multilevel analyses and to offer recommendations to guide the reporting of MLM analysis results. (Contains 2 figures and 2 tables.)

Cluster sampling results in response variable variation both among respondents (i.e., within-cluster or Level 1) and among clusters (i.e., between-cluster or Level 2). Properly modeling within- and between-cluster variation could be of substantive interest in numerous settings, but applied researchers typically test only within-cluster (i.e., individual difference) theories. Specifying a between-cluster model in the absence of theory requires a specification search in multilevel structural equation modeling. This study examined a variety of within-cluster and between-cluster sample sizes, intraclass correlation coefficients, start models, parameter addition and deletion methods, and Type I error control techniques to identify which combination of start model, parameter addition or deletion method, and Type I error control technique best recovered the population of the between-cluster model. Results indicated that a "saturated" start model, univariate parameter deletion technique, and no Type I error control performed best, but recovered the population between-cluster model in less than 1 in 5 attempts at the largest sample sizes. The accuracy of specification search methods, suggestions for applied researchers, and future research directions are discussed. (Contains 4 tables and 10 figures.)

Beginning with Version 11, SPSS implemented the MIXED procedure, which is capable of performing many common hierarchical linear model analyses. The purpose of this article was to provide a tutorial for performing cross-sectional and longitudinal analyses using this popular software platform. In doing so, the authors borrowed heavily from Singer's overview of SAS PROC MIXED, duplicating her analyses using the SPSS MIXED procedure.

Missing data analyses have received considerable recent attention in the methodological literature, and two "modern" methods, multiple imputation and maximum likelihood estimation, are recommended. The goals of this article are to (a) provide an overview of missing-data theory, maximum likelihood estimation, and multiple imputation; (b) conduct a methodological review of missing-data reporting practices in 23 applied research journals; and (c) provide a demonstration of multiple imputation and maximum likelihood estimation using the Longitudinal Study of American Youth data. The results indicated that explicit discussions of missing data increased substantially between 1999 and 2003, but the use of maximum likelihood estimation or multiple imputation was rare; the studies relied almost exclusively on listwise and pairwise deletion. (Contains 5 tables and 3 figures.)

Two methods, direct maximum likelihood (ML) and the expectation maximization (EM) algorithm, can be used to obtain ML parameter estimates for structural equation models with missing data (MD). Although the 2 methods frequently produce identical parameter estimates, it may be easier to satisfy missing at random assumptions using EM. However, no single value of N is applicable to the EM covariance matrix, and this may compromise inferences gained from the model fit statistic and parameter standard errors. The purpose of this study was to identify a value of N that provides accurate inferences when using EM. If all confirmatory factor analysis model indicators have MD, results suggest that the minimum N per covariance term yields honest Type 1 error rates. If MD are restricted to a subset of indicators, the minimum N per variance works well. With respect to standard errors, the harmonic mean N per variance term produces honest confidence interval coverage rates.