The analysis of walking behavior in a physical activity intervention is considered. A Bayesian latent structure modeling approach is proposed whereby the ability and willingness of participants is modeled via latent effects. The dropout process is jointly modeled via a linked survival model. Computational issues are addressed via posterior sampling and a simulated evaluation of the longitudinal model’s ability to recover latent structure and predictor effects is considered. We evaluate the effect of a variety of socio-psychological and spatial neighborhood predictors on the propensity to walk and the estimation of latent ability and willingness in the full study.
Committee PAGA. Physical activities guidelines advisory committee report, Washington, DC: Department of Health and Human Services, 2008.
2.
CarlsonSAFultonJESchoenbornCAet al.Trend and prevalence estimates based on the 2008 physical activity guidelines for Americans. Am J Prev Med2010; 39: 305–313.
3.
HawkinsMSStortiKLRichardsonCRet al.Objectively measured physical activity of USA adults by sex, age, and racial/ethnic groups: A cross-sectional study. Int J Behav Nutr Phys Act2009; 6: 31–31.
4.
OgdenCLCarrolMD. Prevalence of overweight, obesity, and extreme obesity among adults: United States, trends 1976–1980 through 2007–2008, Hyattsville, MD: NCHS Health E-Stat, 2010.
5.
BronfenbrennerU. Making human beings human: Bioecological perspectives on human development, Thousand Oaks, CA: Sage, 2005.
6.
GriffinSFWilsonDKWilcoxSet al.Physical activity influences in a disadvantaged African American community and the communities' proposed solutions. Health Promot Pract2008; 9: 180–190.
7.
WilsonDKTrumpeterNNSt GeorgeSMet al.An overview of the “Positive Action for Today's Health” (PATH) trial for increasing walking in low income, ethnic minority communities. Contemp Clin Trials2010; 31: 624–633.
8.
CoulonSMWilsonDKGriffinSet al.Formative process evaluation for implementing a social marketing intervention to increase walking among African Americans in the Positive Action for Today's Health trial. Am J Public Health2012; 102: 2315–2321.
9.
WilsonDKEllerbeCLawsonABet al.Imputational modeling of spatial context and social environmental predictors of walking in an underserved community: the PATH trial. Spat Spatiotemporal Epidemiol2013; 4: 15–23.
10.
DanielsMHoganJ. Missing data in longitudinal studies: Strategies for Bayesian modeling and sensitivity analysis, New York: Chapman & Hall/CRC, 2008.
11.
GuoXCarlinB. Separate and joint modeling of longitudinal and event time data using standard computer packages. Am Stat2004; 58: 1–9.
12.
HuWLiGLiN. A Bayesian apporach to joint analysis of longitudinal measurments and competing risks failure time data. Stat Med2009; 28: 1601–1619.
13.
HearstMOPatnodeCDSirardJRet al.Multilevel predictors of adolescent physical activity: a longitudinal analysis. Int J Behav Nutr Phys Act2012; 9: 8–8.
14.
WallMMLiR. Multiple indicator hidden Markov model with an application to medical utilization data. Stat Med2009; 28: 293–310.
15.
ThompsonBCoronadoGSnipesSAet al.Methodologic advances and ongoing challenges in designing community-based health promotion programs. Annu Rev Public Health2003; 24: 315–340.
16.
MinklerM. Community-based research partnerships: Challenges and opportunities. J Urban Health: Bull NY Acad Med2003; 82: ii3–ii12.
17.
CampbellMFitzpatrickRHainesAet al.Framework for design and evaluation of complex interventions to improve health. BMJ2000; 321: 694–696.
18.
MorseEVSimonPMBeschCLet al.Issues of recruitment, retention, and compliance in community-based clinical trials with traditionally underserved populations. Appl Nurs Res1995; 8: 8–14.
19.
GorelickPBHarrisYBurnettBet al.The recruitment triangle: Reasons why African Americans enroll, refuse to enroll, or voluntarily withdraw from a clinical trial. J Nat Med Assoc1998; 90: 141–145.
20.
DancyBLWilburJTalashekMet al.Community-based research: Barriers to recruitment of African Americans. Nurs Outlook2004; 52: 234–240.
21.
DeSantisSMBandyopadhyayD. Hidden Markov models for zero-inflated Poisson counts with an application to substance use. Stat Med2011; 30: 1678–1694.
22.
HahnMSassJ. Parameter estimation in continuous time Markov switching models: A semi-continuous Markov chain Monte Carlo approach. Bayes Anal2009; 4: 63–84.
23.
HuangWZegerSLAnthonyJCet al.Latent variable model for joint analysis of multiple repeated measures and bivariate event times. J Am Stat Assoc2001; 96: 906–914.
24.
LinHMcCullochCERosenheckRA. Latent pattern mixture models for informative intermittent missing data in longitudinal studies. Biometrics2004; 60: 295–305.
