Modeling time-location patterns of inner-city high school students in New York and Los Angeles using a longitudinal approach with generalized estimating equations

Publication Status is "Submitted" Or "In Press: 
LDEO Publication: 
Publication Type: 
Year of Publication: 
Journal Title: 
Journal of Exposure Science and Environmental Epidemiology
Journal Date: 
Place Published: 
Tertiary Title: 
Section / Start page: 
ISBN Number: 
ISSN Number: 
Short Title: 
Accession Number: 
LDEO Publication Number: 
Call Number: 

The TEACH Project obtained subjects' time-location information as part of its assessment of personal exposures to air toxics for high school students in two major urban areas. This report uses a longitudinal modeling approach to characterize the association between demographic and temporal predictors and the subjects' time-location behavior for three microenvironments-indoor- home, indoor-school, and outdoors. Such a longitudinal approach has not, to the knowledge of the authors, been previously applied to time-location data. Subjects were 14- to 19-year-old, self reported non-smokers, and were recruited from high schools in New York, NY ( 31 subjects: nine male, 22 female) and Los Angeles, CA ( 31 subjects: eight male, 23 female). Subjects reported their time-location in structured 24-h diaries with 15-min intervals for three consecutive weekdays in each of winter and summer-fall seasons in New York and Los Angeles during 1999-2000. The data set contained 15,009 observations. A longitudinal logistic regression model was run for each microenvironment where the binary outcome indicated the subject's presence in a microenvironment during a 15-min period. The generalized estimating equation ( GEE) technique with alternating logistic regressions was used to account for the correlation of observations within each subject. The multivariate models revealed complex time-location patterns, with subjects predominantly in the indoor-home microenvironment, but also with a clear influence of the school schedule. The models also found that a subject's presence in a particular microenvironment may be significantly positively correlated for as long as 45 min before the current observation. Demographic variables were also predictive of time-location behavior: for the indoor-home microenvironment, having an afterschool job ( OR = 0.67 [ 95% confidence interval: 0.54:0.85]); for indoor-school, living in New York ( 0.42 [ 0.29:0.59]); and for outdoor, being 16-year-old ( 0.80 [ 0.67:0.96]), 17-year-old ( 0.71 [ 0.54:0.92]), and having an afterschool job ( 1.29 [ 1.07:1.56]).


168YYTimes Cited:0Cited References Count:41

DOI 10.1038/sj.jes.7500504