Estimation of Growth Curve Models with Structured Error Covariances by Generalized Estimating Equations

Hwang, Heungsun; Takane, Yoshio

doi:10.2333/bhmk.32.155

Cited by 6 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In GEE, correlation matrix can have different structures which can affect the GEE results. Therefore, five types of working correlation matrix (these are independent, first-order autoregressive, exchangeable, m-dependent and unstructured) were computed, and unstructured model with the lowest quasilikelihood under the independence model criterion (QIC) was chosen in the GEE analysis (41) . Potential variables were included in the analysis.…”

Section: Discussionmentioning

confidence: 99%

The longitudinal relationship between dietary intake, physical activity and muscle strength among adolescents

Hairi

Dahlui

et al. 2020

Br J Nutr

View full text Add to dashboard Cite

The longitudinal relationship between muscle strength, dietary intake and physical activity among adolescents is not well understood. We investigated the trend and longitudinal effects of dietary intakes and physical activity scores on muscle strength in this adolescent. This prospective cohort study consisted of 436 adolescents (134 males; 302 females), aged 13 years at baseline (2012) and were followed up at the age of 15 (2014) and 17 (2016) years, respectively. We measured muscle strength using a calibrated hand dynamometer, estimated dietary intake with a seven-day dietary history and physical activity scores with validated PAQ-C questionnaire. A generalised estimating equation (GEE) used to examine the effect of dietary intakes and physical activity on muscle strength changes. The analysis was performed separately by sex. The muscle strength for males and females had increased within the five-year period. The dietary intakes (energy and macronutrients) also increased initially but plateaued after those aged 15 years for both sexes. Females recorded a significant declining trend in physical activity scores compared to male as they grew older. A significant positive longitudinal relationship was found between protein (β=0.035; p=0.016), carbohydrate intake (β=0.002; p=0.013) and muscle strength among males. However, no longitudinal relationship was found between dietary intake, physical activity and muscle strength among females. Higher protein and carbohydrate intake among males were associated with higher muscle strength but was not observed in females. Nutrition and physical activity focusing on strength building are required in early adolescence and need to be tailored to males and females accordingly.

show abstract

Section: Discussionmentioning

confidence: 99%

The longitudinal relationship between dietary intake, physical activity and muscle strength among adolescents

Hairi

Dahlui

et al. 2020

Br J Nutr

View full text Add to dashboard Cite

show abstract

“…It is commonly used in conjunction with time-constant explanatory variables to explain the variation in the growth random effects. Hwang and Takane [14] also pointed out that the conventional GCM assumes that the covariance matrix of repeated measurements is unstructured. Typically, GCM in the social sciences is normally used with a relatively small and equal number of time points for each subject.…”

Section: Mixed-effects Modellingmentioning

confidence: 98%

Modelling escalation in crime seriousness: a latent variable approach

Francis

Liu

2015

METRON

View full text Add to dashboard Cite

This paper investigates the use of latent variable models in assessing escalation in crime seriousness. It has two aims. The first is to contrast a mixed-effects approach to modelling crime escalation with a latent variable approach. The paper therefore examines whether there are specific subgroups of offenders with distinct seriousness trajectory shapes. The second is methodological-to compare mixed-effects modelling used in previous work on escalation with group-based trajectory modelling and growth mixture modelling (mixture of mixed-effects models). The availability of software is an issue, and comparisons of fit across software packages is not straightforward. We suggest that mixture models are necessary in modelling crime seriousness, that growth mixture models rather than group-based trajectory models provide the best fit to the data, and that R gives the best software environment for comparing models. Substantively, we identify three latent groups, with the largest group showing crime seriousness increases with criminal justice experience (measured through number of conviction occasions) and decreases with increasing age. The other two groups show more dramatic non-linear effects with age, and non-significant effects of criminal justice experience. Policy considerations of these results are briefly discussed.

show abstract

Generalized Linear Models

2018

Mathematical Statistics

View full text Add to dashboard Cite

The term "generalized linear models" encompasses both a class of models and a style of thinking about building models that is applicable to a wide variety of distributions and types of responses. Key elements are a distributional assumption for the data and a transformation of the mean which is assumed to create a linear model for the predictors. The history of generalized linear models 1s traced, current work is reviewed and some predictions are made.

show abstract

Estimation of Growth Curve Models with Structured Error Covariances by Generalized Estimating Equations

Cited by 6 publications

References 25 publications

The longitudinal relationship between dietary intake, physical activity and muscle strength among adolescents

The longitudinal relationship between dietary intake, physical activity and muscle strength among adolescents

Modelling escalation in crime seriousness: a latent variable approach

Generalized Linear Models

Contact Info

Product

Resources

About