Analysis of prevention program effectiveness with clustered data using generalized estimating equations.

Experimental studies of prevention programs often randomize clusters of individuals rather than individuals to treatment conditions. When the correlation among individuals within clusters is not accounted for in statistical analysis, the standard errors are biased, potentially resulting in misleading conclusions about the significance of treatment effects. This study demonstrates the generalized estimating equations (GEE) method, focusing specifically on the GEE-independent method, to control for within-cluster correlation in regression models with either continuous or binary outcomes. The GEE-independent method yields consistent and robust variance estimates. Data from project DARE, a youth substance abuse prevention program, are used for illustration.

Long-term evaluation of drug abuse resistance education.

Project DARE (Drug Abuse Resistance Education) is the most prevalent school-based drug-use prevention program in the United States, but there is little evidence of its effectiveness. Results from a longitudinal evaluation of the program in 36 schools in Illinois provide only limited support for DARE's impact on student's drug use immediately following the intervention, and no support for either continued or emerging impact on drug use 1 or 2 years after receiving DARE instruction. In addition, DARE had only limited positive effects on psychological variables (i.e., self-esteem) and no effect on social variables (e.g., peer resistance skills). Possible substantive and methodological explanations for the relative lack of DARE's effectiveness observed in this study are discussed.

Ratio estimates, the delta method, and quantal response tests for increased carcinogenicity.

This paper demonstrates the use of the delta method for estimating the variance of ratio statistics derived from animal carcinogenicity experiments. The Cochran-Armitage test (Cochran, 1954, Biometrika 10, 417-451; and Armitage, 1955, Biometrics 11, 375-386) is routinely applied to carcinogenicity data as a test for linear trend in lifetime tumor incidence rates. The computing formula for this test derives from the assumption that the denominators of the quantal response rates are fixed. However, when time-at-risk weights are introduced to correct for treatment-related differences in survival, the denominators of the quantal response rates are subject to random variation. The delta method and weighted least squares techniques are applied here to approximate the variance of such ratio statistics and test for a linear dose-response relationship among treatments. This technique is compared to that of Bailer and Portier (1988, Biometrics 44, 417-431), who introduced a survival-adjusted quantal response test for trend in lifetime tumor incidence rates. Their test modifies the usual Cochran-Armitage computing formula by weighting the denominators of the response rates to reflect less-than-whole-animal contributions to risk. Within the framework of a weighted least squares linear regression model that underlies the Cochran-Armitage test, the time-at-risk weights of Bailer and Portier are incorporated using the delta method. Although the delta method approach is slightly more computationally intensive, small-sample simulations indicate that it has superior operating characteristics over the Poly-3 trend test of Bailer and Portier when background tumor incidence rates are low (under 3%) and survival patterns differ markedly across treatments.(ABSTRACT TRUNCATED AT 250 WORDS)

Cluster sampling techniques in quantal response teratology and developmental toxicity studies.

This paper presents a model-free approach for evaluating teratology and developmental toxicity data involving clustered binary responses. In teratology studies, a major statistical problem arises from the effect of intralitter correlation, or the potential for littermates to respond similarly. Some statistical methods impose strict distributional assumptions to account for extra-binomial variation, while others rely on nonparametric resampling and empirical variance estimation techniques. Quasi-likelihood methods and generalized estimating equations (GEE), which model the marginal mean/variance relationship, also avoid strict distributional assumptions. The proposed approach, often used to analyze complex sample survey data, is based on a first-order Taylor series approximation and a between-cluster variance estimation procedure, yielding consistent variance estimates for binomial-based proportions and regression coefficients from dose-response models. The cluster sample technique, presented here in the context of a logistic dose-response model, incorporates many of the advantages of quasi-likelihood methods, are valid for any underlying nested correlation structure, and are adaptable to a variety of analytical settings. The results of a simulation study show the cluster sample technique to be a viable competitor to GEE methods currently receiving attention.

Developmental neurotoxicity evaluation of orally administered isopropanol in rats.

Isopropanol was administered by gavage to timed-mated rats from Gestation Day (GD) 6 through Postnatal Day (PND) 21. Doses administered were 0, 200, 700, or 1200 mg/kg/day in a volume of 5 ml/kg. The dams were allowed to deliver and body weights and food consumption were recorded during gestation and lactation. Pups were counted, examined, sexed, and weighed on PND 0, 4, 7, 13, 17, 21, 36, 49, and 68. Litters were culled to eight pups (4:4 or 5:3 sex ratio) on PND 4 and litters without acceptable numbers of male and female pups were eliminated from the study. Pups were weaned on PND 22, and two pups from each litter and their dams were killed. Six of these pups from each dose group were perfused in situ for histopathological examination of the central and peripheral nervous system. Brains of the remaining pups were divided into four regions and weighed. Maternal liver and kidney weights were recorded. Weaned pups were assessed for day of testes descent or vaginal opening and for motor activity on PNDs 13, 17, 21, 47, and 58; auditory startle on PNDs 22 and 60; and active avoidance on PNDs 60-64. These pups were euthanized and examined on PND 68. One high-dose dam died on PND 15, but there were no other clinical observations or effects on maternal weight, food consumption, or gestation length. Pup survival, weight, sex ratio, and sexual maturation were unaffected. There were no biologically significant findings in the behavioral tests, no changes in organ weights, and no pathological findings that could be attributed to isopropanol exposure. In conclusion, there was no evidence of developmental neurotoxicity associated with isopropanol exposure as high as 1200 mg/kg/day.