Search

We propose a transition model for analysing data from complex longitudinal studies. Because missing values are practically unavoidable in large longitudinal studies, we also present a two-stage imputation method for handling general patterns of missing values on both the outcome and the covariates by combining multiple imputation with stochastic regression imputation. Our model is a time-varying autoregression on the past innovations (residuals), and it can be used in cases where general dynamics must be taken into account, and where the model selection is important. The entire estimation process was carried out using available procedures in statistical packages such as SAS and S-PLUS. To illustrate the viability of the proposed model and the two-stage imputation method, we analyse data collected in an epidemiological study that focused on various factors relating to childhood growth. Finally, we present a simulation study to investigate the behaviour of our two-stage imputation procedure. Copyright © 2006 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

We prospectively examined the relationship between prenatal tobacco exposure (PTE) and child behavior in a birth cohort of 357 offspring of teenage mothers. PTE was defined as any exposure across pregnancy and, in separate analyses, exposure within each trimester. Outcomes included measures of behavior problems, activity, and attention. On average, the children were 6.4 years of age, 48% were females, and 69% were Black. Data on maternal tobacco and other substance use were collected prenatally and postnatally: 46% of the mothers smoked in the first trimester and 58% smoked 6 years later. Child urinary cotinine measured exposure to environmental tobacco smoke (ETS). Stepwise multiple regressions were run. PTE predicted significantly increased offspring activity; impulsivity; and aggression, externalizing, and total behavior problems in step 1. PTE remained a significant predictor of increased activity when maternal psychological characteristics, home environment, and ETS were added. The results were similar when PTE was examined by trimesters, although later pregnancy tobacco exposure predicted the most behavioral outcomes. In the final model, PTE (all three trimesters) and PTE (second trimester) were significant predictors of increased activity and attention problems, respectively. Other predictors of child behavior included maternal anxiety, depression, hostility, and home environment. ETS was not a significant predictor of child behavior when PTE was considered. Smoking during pregnancy among adolescents is a significant predictor of increased activity and attention problems in their offspring after controlling for covariates in the prenatal and current environments. Smoking cessation interventions are recommended for this population to avoid the effects of PTE on the offspring of pregnant adolescents. This is particularly important because these mothers will likely become pregnant again and many will increase their level of tobacco use as they mature. [ABSTRACT FROM AUTHOR]

Few studies have considered the etiological role of the fetal environment on the offspring's substance use. This prospective study examines the relations between the mother's prenatal and current smoking and the offspring's smoking experimentation. A low SES birth cohort of 589 10-year-olds, who have been followed since their gestation, completed a self-report questionnaire about their substance use. Half were female, and 52% were African-American. Detailed data on exposure to tobacco and other substances in the prenatal and postnatal periods were collected from the mothers. During pregnancy, 52.6% of the mothers were smokers; 59.7% were smokers when their children were 10. Six per cent of the children (37/589) reported ever smoking cigarettes, 3% had had one full alcoholic drink, and none had started to use other drugs. Maternal smoking during pregnancy was significantly associated with an increased risk of the child's tobacco experimentation. Offspring exposed to more than 1/2 pack per day during gestation had a 5.5-fold increased risk for early experimentation. Structural equation modeling showed that prenatal tobacco exposure had a direct and significant effect on the child's smoking and that maternal current smoking was not significant. Prenatal tobacco exposure also predicted child anxiety/depression and externalizing behaviors, and these outcomes affected child smoking through the mediating effect of peer tobacco use. [ABSTRACT FROM AUTHOR]

Recent discussions of the functional significance of ultradian rhythms emphasize their importance to human physiology. Over the past 25 years, electroencephalographic (EEG) sleep patterns have been used in assessing the cerebral and central nervous system maturation of neonates. Through an interdisciplinary effort, spectral (Fourier) methods have been developed to discriminate between the various stages of sleep based on EEG recordings. Nevertheless, there has been little effort to develop methods for the statistical analysis of sleep-state cycling. In particular, attention has primarily been focused on the ultradian rhythm of sleep as it cycles between two states, active or rapid eye movement (REM) and quiet or non-REM sleep. There are, however, several components of REM and non-REM sleep, as well as a transitional state (indeterminate sleep) and abrupt alterations of state (arousal). Moreover, few studies have investigated the effects of prenatal alcohol exposure on the neurophysiological development of infants as assessed through sleep or EEG patterns. In this article the theory of Walsh-Fourier analysis for discrete-valued (categorical) time series is used to investigate the spectral components of EEG sleep-state patterns of infants whose mothers abstained from drinking during pregnancy, and infants of mothers who used moderate amounts of alcohol continuously during pregnancy. The sample for this study is part of a larger cohort of women participating in a longitudinal study of substance use during pregnancy. The analysis is based on the finite Walsh-Fourier transform that is defined in terms of the Walsh functions. The square-wave Walsh functions form a complete orthonormal sequence on [0, 1) and take... [ABSTRACT FROM AUTHOR]