peer smoking on adolescents' own smoking is still a matter of debate. In addition, little research has examined the role of sign8cant others' behavior on different stages of smoking onset. In particular, not much information is available regarding gender and ethnic differences in social influences on smoking behavior. We use structural equation modeling to address these issues. Different theoretical perspectives from cognitive-affective theories (Ajzen 1985; Ajzen and Fishbein 1980) and social learning theories (Akers et al. 1979; Bandura 1969, 1982, 1986) have been integrated into a structural model of smoking influence. The results show that friends' smoking affects adolescent initiation into smoking both directly and indirectly, whereas parental smoking influences smoking initiation only indirectly. The data also show that friends' and parents' smoking affect smoking escalation only indirectly. In general, friends' smoking has a stronger effect on adolescents' smoking behavior, particularly on initiation. Multiple group comparisons of the structural models predicting smoking initiation among males and females reveal that parental approval of smoking plays a sign8cant mediating role for females, but not for males. Comparisons of Whites, Blacks, Hispanics, and other ethnic groups reveal that there are some signiJicant differences in the pathways of friends' influences among the four groups.

In recent years, the use of the last observation carried forward (LOCF) approach in imputing missing data in clinical trials has been greatly criticized, and several likelihood-based modeling approaches are proposed to analyze such incomplete data. One of the proposed likelihood-based methods is the Mixed-Effect Model Repeated Measure (MMRM) model. To compare the performance of LOCF and MMRM approaches in analyzing incomplete data, two extensive simulation studies are conducted, and the empirical bias and Type I error rates associated with estimators and tests of treatment effects under three missing data paradigms are evaluated. The simulation studies demonstrate that LOCF analysis can lead to substantial biases in estimators of treatment effects and can greatly inflate Type I error rates of the statistical tests, whereas MMRM analysis on the available data leads to estimators with comparatively small bias, and controls Type I error rates at a nominal level in the presence of missing completely at random (MCAR) or missing at random (MAR) and some possibility of missing not at random (MNAR) data. In a sensitivity analysis of 48 clinical trial datasets obtained from 25 New Drug Applications (NDA) submissions of neurological and psychiatric drug products, MMRM analysis appears to be a superior approach in controlling Type I error rates and minimizing biases, as compared to LOCF ANCOVA analysis. In the exploratory analyses of the datasets, no clear evidence of the presence of MNAR missingness is found.

Most school-based smoking prevention studies employ designs in which schools or classrooms are assigned to different treatment conditions while observations are made on individual students. This design requires that the treatment effect be assessed against the between-school variance. However, the between-school variance is usually larger than the variance that would be obtained if students were individually randomized to different conditions. Consequently, the power of the test for a treatment effect is reduced, and it becomes difficult to detect important treatment effects. To assess the potential loss of power or to calculate appropriate sample sizes, investigators need good estimates of the intraclass correlations for the variables of interest. The authors calculated intraclass correlations for some common outcome variables in a school-based smoking prevention study, using a three-level model-i.e., students nested within classrooms and classrooms nested within schools. The authors present the intraclass correlation estimates for the entire data set, as well as separately by sex and ethnicity. They also illustrate the use of these estimates in the planning of future studies.

This research examines the relative importance of parental and friends' influences on adolescents' smoking behavior and changes in the effects of social influences during adolescence. Data were collected at 4 times from 7th to 9th grades. Random‐effects ordinal regression models were employed to predict the repeated classification of adolescent smoking status using time effects, prior smoking status, friends' smoking, and parental smoking. In general, the effects of friends' smoking are stronger than those of parental smoking, and these differences increase over time. In addition, friends' smoking has greater effects on nonsmokers than smokers. Separate models for males and females disclose some gender differences. In particular, the effects of friends' smoking are stronger for females than for males, and the increasing trend of friends' influences is more noticeable for females than for males. Models for 4 ethnic groups also suggest differential susceptibility to social influences in different cultures.

No abstract

The last-observation-carried-forward imputation method is commonly used for imputting data missing due to dropouts in longitudinal clinical trials. The method assumes that outcome remains constant at the last observed value after dropout, which is unlikely in many clinical trials. Recently, random-effects regression models have become popular for analysis of longitudinal clinical trial data with dropouts. However, inference obtained from random-effects regression models is valid when the missing-at-random dropout process is present. The random-effects pattern-mixture model, on the other hand, provides an approach that is valid under more general missingness mechanisms. In this article we describe the use of random-effects pattern-mixture models under different patterns for dropouts. First, subjects are divided into groups depending on their missing-data patterns, and then model parameters are estimated for each pattern. Finally, overall estimates are obtained by averaging over the missing-data patterns and corresponding standard errors are obtained using the delta method. A typical longitudinal clinical trial data set is used to illustrate and compare the above methods of data analyses in the presence of missing data due to dropouts.

Abstract. Parkinson's disease is an age-related degenerative disorder of the central nervous system that often impairs the sufferer's motor skills and speech, as well as other functions. Symptoms can include tremor, stiffness, slowness of movement, and impaired balance. An estimated four million people worldwide suffer from the disease, which usually affects people over the age of 60. Presently, there is no precedent for approving any drug as having a modifying effect (i.e., slowing or delaying) for disease progression of Parkinson's disease. Clinical trial designs such as delayed start and withdrawal are being proposed to discern symptomatic and protective effects. The current work focused on understanding the features of delayed start design using prior knowledge from published and data submitted to US Food and Drug Administration (US FDA) as part of drug approval or protocol evaluation. Clinical trial simulations were conducted to evaluate the false-positive rate, power under a new statistical analysis methodology, and various scenarios leading to patient discontinuations from clinical trials. The outcome of this work is part of the ongoing discussion between the US FDA and the pharmaceutical industry on the standards required for demonstrating disease-modifying effect using delayed start design.

Random-effects regression modelling is proposed for analysis of correlated grouped-time survival data. Two analysis approaches are considered. The first treats survival time as an ordinal outcome, which is either right-censored or not. The second approach treats survival time as a set of dichotomous indicators of whether the event occurred for time periods up to the period of the event or censor. For either approach both proportional hazards and proportional odds versions of the random-effects model are developed, while partial proportional hazards and odds generalizations are described for the latter approach. For estimation, a full-information maximum marginal likelihood solution is implemented using numerical quadrature to integrate over the distribution of multiple random effects. The quadrature solution allows some flexibility in the choice of distributions for the random effects; both normal and rectangular distributions are considered in this article. An analysis of a dataset where students are clustered within schools is used to illustrate features of random-effects analysis of clustered grouped-time survival data.