A design for studying the clustering of plant or animal species using quadrat sizes in geometric progression.
Explore the source record for details and available documents.
Mathematics↗
Biomedical subjects
R L Prentice
Publications and source records attributed to R L Prentice.
Design considerations for estimation of exposure effects on disease risk, using aggregate data studies.
Previously we proposed an aggregate data study design for estimation of exposure effects from population-based disease rates and covariate data from risk factor surveys in each population group. A basic relative rate model specified for individuals is aggregated to produce a random effects relative rate model for the disease rates. Relative rate parameter estimates from aggregate data studies target the same parameters as individual-level studies but use between-group information in the data. We distinguish aggregate data studies from ecologic studies. Considerations in the design of aggregate studies are motivated by the need to gain clearer understanding of the role of diet in cancer aetiology. Simulation studies show that increasing the number of populations included in an aggregate data study from about 20 to 30-40 gives greater improvement in power than corresponding increases in the size of the survey sample in each population over an initial size of 100 individuals.
Aged↗
On non-parametric maximum likelihood estimation of the bivariate survivor function.
The likelihood function for the bivariate survivor function F, under independent censorship, is maximized to obtain a non-parametric maximum likelihood estimator &Fcirc;. &Fcirc; may or may not be unique depending on the configuration of singly- and doubly-censored pairs. The likelihood function can be maximized by placing all mass on the grid formed by the uncensored failure times, or half lines beyond the failure time grid, or in the upper right quadrant beyond the grid. By accumulating the mass along lines (or regions) where the likelihood is flat, one obtains a partially maximized likelihood as a function of parameters that can be uniquely estimated. The score equations corresponding to these point mass parameters are derived, using a Lagrange multiplier technique to ensure unit total mass, and a modified Newton procedure is used to calculate the parameter estimates in some limited simulation studies. Some considerations for the further development of non-parametric bivariate survivor function estimators are briefly described.
Computer Simulation↗
Aspects of the use of relative risk models in the design and analysis of cohort studies and prevention trials.
Relative risk regression methods provide a unifying and powerful approach to a range of problems in the design and analysis of cohort studies and prevention trials. Standard partial likelihood-based estimation procedures do not, however, encompass several features that are important in such contexts. Specifically, one may wish to relate disease rates marginally to 'recent' risk factor measurements, whereas a partial likelihood approach requires one to condition on an accumulating risk factor history. Secondly, risk factor values may be ascertained with considerable measurement error, thereby requiring specialized procedures to estimate relative risk parameters. Thirdly, analysis of raw materials to obtain desired covariate (risk factor) histories may involve considerable expense if carried out for the entire cohort. Case-control and case-cohort sampling procedures can avoid much of this expense, but once again partial likelihood estimation procedures require generalization. Such generalizations are described herein.
Blood Pressure↗
Opportunities for enhancing efficiency and reducing cost in large scale disease prevention trials: a statistical perspective.
Randomized intervention trials play an important role in the identification of practical approaches to reducing major chronic diseases in our society. Very few such trials are likely to be possible, however, in coming years unless we adopt procedures less demanding and less costly than those used in the past. Towards this end some elements of an efficient prevention trial are discussed, including aspects of study design, criteria for eligibility and exclusion, procedures for data collection, follow-up, endpoint ascertainment, and data analysis, and for ancillary studies. For example, possibilities for enhancing efficiency in the use of endpoint events include the selection of an appropriately weighted test statistic, the use of case-control or case-cohort sampling procedures in the processing of covariate data and specimens, and the notion of replacing a disease endpoint by an earlier or less expensive surrogate endpoint. Ideas for enhancing the efficiency of prevention trials will be illustrated in the context of a proposed Dietary Fat Intervention Trial for disease prevention in women.
Adult↗
Relationship between longitudinal changes in blood pressure and stroke incidence.
The relationship of changes in blood pressure with time to stroke incidence was examined on members of the Adult Health Study sample who have participated in biennial clinical examinations at the Radiation Effects Research Foundation since their inception in 1958. The regression coefficient of blood pressure regressed on time (the increase in blood pressure per cycle) was used as an index of the change in blood pressure with time. Cox's regression analysis, a technique which is suitable for follow-up studies was used. The data suggest that a single blood pressure measurement is not sufficient for predicting risk; the accumulated value or average over a period of time should be considered for this purpose. In addition to the actual blood pressure, the increase in blood pressure with time is a risk factor, particularly for cerebral hemorrhage. Cerebral hemorrhage was more strongly related to diastolic than to systolic blood pressure, while cerebral infarction appeared to be more strongly related to systolic than to diastolic blood pressure.
Adult↗
Maintenance of a low-fat diet: follow-up of the Women's Health Trial.
This report examines the maintenance of a low-fat diet 1 year on average after the completion of intervention sessions among participants in the Women's Health Trial (WHT). The WHT was a randomized controlled trial of the feasibility of adoption of a low-fat diet among women of moderate or increased risk of breast cancer, conduced in Seattle, Houston, and Cincinnati in 1985-1988. The women randomized to the low-fat diet attended an intensive dietary intervention program for 5-37 months. Intervention women were highly successful in reducing their dietary fat intake from 40.0% of energy intake at baseline to 26.3% by the end of the trial, based on a food frequency questionnaire (or an estimated 24% adjusted for the inaccuracies of a food frequency questionnaire versus a 4-day diet record). During 1989, 1 year on average after the WHT ended, 448 intervention women and 457 control women (87% of eligibles) completed a follow-up survey to determine the degree of maintenance of the diet. The intervention women maintained the low-fat diet with an increase of only 1.4 percentage points of energy from fat, despite the fact that they had attended no further intervention sessions and had made no commitment to maintain the diet beyond the end of the WHT. Furthermore, the degree of maintenance of the low-fat diet was not dependent on the length of time in the intervention, which suggests that intervention led to a sustained change in eating habits after as little as 5-9 months (8-13 classes).(ABSTRACT TRUNCATED AT 250 WORDS)
Aged↗