Obesity

Transition from adolescence to adulthood and feedback partial gmm logistic model with time-dependent covariates

Di Fang, Kyle M. Irimata, Rachael N. Rhodes, Jeffrey Wilson

Research output: Contribution to journalArticle

Abstract

Background: The aim of this study is to investigate the impact of certain covariates on obesity. More importantly, we seek to determine the feedback of obesity on depression, and physical activity as they transition from adolescence to young adulthood. Methods: Using 15 years of nationally representative data from 6560 adolescents (Add health data), we estimate feedback and associations between depression, and activity scale on obesity while we adjusted for gender, age, race/ethnicity, socioeconomic status through a GMM logistic regression model with time-dependent covariates. Results: Activity (p<0.001) and depression (p<0.001) have significant impact on Obesity. In early years, alcohol had no impact (p=0.895 and p=0.476) on obesity but in later years it did (p<0.001). In the early years, television hours had an impact but as they got older, it did not. Conclusion: Our findings suggest that public health researchers can target obesity simultaneously with depression, and activity scale. These findings contribute new insights into the feedback of obesity on depression, and activity. This unique model allows segments of associations to be addressed rather than assuming all associations remain the same over 15 years.

Original languageEnglish (US)
JournalEpidemiology Biostatistics and Public Health
Volume16
Issue number1
DOIs
StatePublished - Jan 1 2019

Fingerprint

Obesity
Logistic Models
Television
Social Class
Public Health
Alcohols
Research Personnel
Exercise

Keywords

  • Activity scale
  • Depression
  • Obesity
  • Time-dependent covariates

ASJC Scopus subject areas

  • Epidemiology
  • Health Policy
  • Community and Home Care
  • Public Health, Environmental and Occupational Health

Cite this

Obesity : Transition from adolescence to adulthood and feedback partial gmm logistic model with time-dependent covariates. / Fang, Di; Irimata, Kyle M.; Rhodes, Rachael N.; Wilson, Jeffrey.

In: Epidemiology Biostatistics and Public Health, Vol. 16, No. 1, 01.01.2019.

Research output: Contribution to journalArticle

@article{e572b10cce0d4cd9ab5366e44c20364c,
title = "Obesity: Transition from adolescence to adulthood and feedback partial gmm logistic model with time-dependent covariates",
abstract = "Background: The aim of this study is to investigate the impact of certain covariates on obesity. More importantly, we seek to determine the feedback of obesity on depression, and physical activity as they transition from adolescence to young adulthood. Methods: Using 15 years of nationally representative data from 6560 adolescents (Add health data), we estimate feedback and associations between depression, and activity scale on obesity while we adjusted for gender, age, race/ethnicity, socioeconomic status through a GMM logistic regression model with time-dependent covariates. Results: Activity (p<0.001) and depression (p<0.001) have significant impact on Obesity. In early years, alcohol had no impact (p=0.895 and p=0.476) on obesity but in later years it did (p<0.001). In the early years, television hours had an impact but as they got older, it did not. Conclusion: Our findings suggest that public health researchers can target obesity simultaneously with depression, and activity scale. These findings contribute new insights into the feedback of obesity on depression, and activity. This unique model allows segments of associations to be addressed rather than assuming all associations remain the same over 15 years.",
keywords = "Activity scale, Depression, Obesity, Time-dependent covariates",
author = "Di Fang and Irimata, {Kyle M.} and Rhodes, {Rachael N.} and Jeffrey Wilson",
year = "2019",
month = "1",
day = "1",
doi = "10.2427/13022",
language = "English (US)",
volume = "16",
journal = "Epidemiology Biostatistics and Public Health",
issn = "2282-2305",
publisher = "Prex",
number = "1",

}

TY - JOUR

T1 - Obesity

T2 - Transition from adolescence to adulthood and feedback partial gmm logistic model with time-dependent covariates

AU - Fang, Di

AU - Irimata, Kyle M.

AU - Rhodes, Rachael N.

AU - Wilson, Jeffrey

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Background: The aim of this study is to investigate the impact of certain covariates on obesity. More importantly, we seek to determine the feedback of obesity on depression, and physical activity as they transition from adolescence to young adulthood. Methods: Using 15 years of nationally representative data from 6560 adolescents (Add health data), we estimate feedback and associations between depression, and activity scale on obesity while we adjusted for gender, age, race/ethnicity, socioeconomic status through a GMM logistic regression model with time-dependent covariates. Results: Activity (p<0.001) and depression (p<0.001) have significant impact on Obesity. In early years, alcohol had no impact (p=0.895 and p=0.476) on obesity but in later years it did (p<0.001). In the early years, television hours had an impact but as they got older, it did not. Conclusion: Our findings suggest that public health researchers can target obesity simultaneously with depression, and activity scale. These findings contribute new insights into the feedback of obesity on depression, and activity. This unique model allows segments of associations to be addressed rather than assuming all associations remain the same over 15 years.

AB - Background: The aim of this study is to investigate the impact of certain covariates on obesity. More importantly, we seek to determine the feedback of obesity on depression, and physical activity as they transition from adolescence to young adulthood. Methods: Using 15 years of nationally representative data from 6560 adolescents (Add health data), we estimate feedback and associations between depression, and activity scale on obesity while we adjusted for gender, age, race/ethnicity, socioeconomic status through a GMM logistic regression model with time-dependent covariates. Results: Activity (p<0.001) and depression (p<0.001) have significant impact on Obesity. In early years, alcohol had no impact (p=0.895 and p=0.476) on obesity but in later years it did (p<0.001). In the early years, television hours had an impact but as they got older, it did not. Conclusion: Our findings suggest that public health researchers can target obesity simultaneously with depression, and activity scale. These findings contribute new insights into the feedback of obesity on depression, and activity. This unique model allows segments of associations to be addressed rather than assuming all associations remain the same over 15 years.

KW - Activity scale

KW - Depression

KW - Obesity

KW - Time-dependent covariates

UR - http://www.scopus.com/inward/record.url?scp=85064330355&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064330355&partnerID=8YFLogxK

U2 - 10.2427/13022

DO - 10.2427/13022

M3 - Article

VL - 16

JO - Epidemiology Biostatistics and Public Health

JF - Epidemiology Biostatistics and Public Health

SN - 2282-2305

IS - 1

ER -