Group-based Trajectory Modeling Extended to Account for Nonrandom Participant Attrition

Haviland, Amelia; Jones, Bobby; Nagin, Daniel S.

doi:10.1177/0049124111400041

Cited by 168 publications

(163 citation statements)

References 30 publications

Supporting

Mentioning

160

Contrasting

Order By: Relevance

“…In this model extension, each trajectory group is described by a trajectory and the probability of trajectory group membership at baseline and also by the probability of dropout for each period after baseline. This extension is described in Haviland et al [19]. …”

Section: An Illustration Of Gbtmmentioning

confidence: 99%

Group-Based Trajectory Modeling: An Overview

Nagin¹

2014

Ann Nutr Metab

Self Cite

424

361

View full text Add to dashboard Cite

This article provides an overview of a group-based statistical methodology for analyzing developmental trajectories - the evolution of an outcome over age or time. Across all application domains, this group-based statistical method lends itself to the presentation of findings in the form of easily understood graphical and tabular data summaries. In so doing, the method provides statistical researchers with a tool for figuratively painting a statistical portrait of the predictors and consequences of distinct trajectories of development. Data summaries of this form have the great advantage of being accessible to nontechnical audiences and quickly comprehensible to audiences that are technically sophisticated. Examples of the application of the method are provided. A detailed account of the statistical underpinnings of the method and a full range of applications are provided by the author in a previous study.

show abstract

Section: An Illustration Of Gbtmmentioning

confidence: 99%

Group-Based Trajectory Modeling: An Overview

Nagin¹

2014

Ann Nutr Metab

Self Cite

424

361

View full text Add to dashboard Cite

show abstract

“…We then conducted the following sensitivity analyses to further assess the potential impact of missing data: we recalculated median values of HRQoL measures after multiple imputation of missing values using 5 imputed data sets (31) (IBM SPSS software, version 24), repeated Kaplan Meier analyses on each of 5 imputed data sets, and repeated the latent trajectory analysis with the drop-out function for nonrandom attrition in PROC TRAJ (32).…”

Section: Significance and Innovationsmentioning

confidence: 99%

Health‐Related Quality of Life in an Inception Cohort of Children With Juvenile Idiopathic Arthritis: A Longitudinal Analysis

Oen

Guzman

Dufault

et al. 2017

Arthritis Care & Research

View full text Add to dashboard Cite

Objective. To describe changes in health-related quality of life (HRQoL) over time in children with juvenile idiopathic arthritis (JIA), relative to other outcomes, and to identify predictors of unfavorable HRQoL trajectories. Methods. Children with JIA in the Research in Arthritis in Canadian Children emphasizing Outcomes (ReACCh-Out) cohort were included. The Juvenile Arthritis Quality of Life Questionnaire (JAQQ, a standardized instrument), healthrelated Quality of My Life (HRQoML, an instrument based on personal valuations), and JIA core variables were completed serially. Analyses included median values, Kaplan-Meier survival curves, and latent trajectory analysis. Results. A total of 1,249 patients enrolled at a median of 0.5 months after diagnosis were followed for a median of 34.2 months. The degree of initial HRQoL impairment and probabilities of reaching the best possible HRQoL scores varied across JIA categories (best for oligoarthritis, worst for rheumatoid factor-positive polyarthritis). Median times to attain best possible HRQoL scores (JAQQ 59.3 months, HRQoML 34.5 months), lagged behind those for disease activity, pain, and disability measures. Most patients followed trajectories with minimal or mild impairment; however, 7.6% and 13.8% of patients, respectively, followed JAQQ and HRQoML trajectories with persistent major impairment in HRQoL. JIA category, aboriginal ethnicity, and baseline disease activity measures distinguished between membership in trajectories with major and minimal impairments. Conclusion. Improvement in HRQoL is slower than for disease activity, pain, and disability. Improvement of a measure based on respondents' preferences (HRQoML) is more rapid than that of a standardized measure (JAQQ). Higher disease activity at diagnosis heralds an unfavorable HRQoL trajectory.

show abstract

“…CCIs are modeled using a Poisson distribution with quadratic functions, which are suitable given that age patterns in CCI are non-linear. The probability of dying at a given age is modeled simultaneously (Haviland, Jones, and Nagin 2011;Zimmer et al 2012). Patterns of morbidity and mortality risks are sex-specific.…”

Section: Constructing Morbidity Trajectory Groupsmentioning

confidence: 99%

“…These trajectories also incorporate mortality probabilities within the modeling. Incorporating rather than excluding mortality means that the end of life is considered as part of a developmental process of old-age health (Haviland, Jones, and Nagin 2011).…”

Section: Introductionmentioning

confidence: 99%