Search PubMed⌕ Search
Home/Archive/PubMed

PubMed · 2814072

Analysis of epidemiologic case-base studies for binary data.

M Nurminen
View original source ↗Export metadata ↓

Abstract

Recent developments in statistical methods for epidemiology have revived the application of sampling techniques in the design and analysis of cohort studies. The 'case-base' design involves sampling of both the cases and the cohort base of the study. This paper reviews some data-analytic imperfections of the approaches to risk ratio estimation, and modifies and advances a consistent likelihood-based procedure-analogous to Miettinen and Nurminen's proposal for a full cohort design--for interval estimation (and also point estimation and significance testing) in the context of binary case-base data. First, the procedure avoids the use of Taylor-series approximations to derive variance estimators for non-linear functions of parameters. Second, the asymptotic condition effects a simple computational expression for the chi-square function of risk ratios that is universally applicable to small samples. The statistical modelling underlying the method allows inferences about risk ratios without the assumption of rare disease either for the general population or for a particular base. The paper also extends the analysis to encompass stratified data. Finally, a numerical evaluation evinced the accurate small-sample properties of the proposed method.

Explore related subjects

Binomial DistributionCase-Control StudiesChi-Square DistributionCohort StudiesConfidence IntervalsLikelihood FunctionsOdds RatioPoisson DistributionProbabilitySampling StudiesJournal Article

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

M Nurminen. 1989. Analysis of epidemiologic case-base studies for binary data.. https://doi.org/10.1002/sim.4780081008

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2007

Early stopping clinical trials of binomial response with an exact group sequential method.

In Phase II clinical trials much slower patient enrollment and intervening results of comparable trials can make it desirable to stop trials early when the data indicate no relevant effect. For a binomial response, we adopt an exact group sequential method as a decision tool to assess whether the trial could be stopped early or not. We have applied the exact group sequential method to a Phase II Tuberculosis clinical trial, and the results have been compared with that from error spending and conditional power approaches. We conclude that the exact group sequential method is more efficient for interim analysis in clinical trials than the error spending and conditional power approaches. Published in 2007 by John Wiley & Sons, Ltd.

Binomial Distribution↗
PubMed2006

Computational simulations of vocal fold vibration: Bernoulli versus Navier-Stokes.

The use of the mechanical energy (ME) equation for fluid flow, an extension of the Bernoulli equation, to predict the aerodynamic loading on a two-dimensional finite element vocal fold model is examined. Three steady, one-dimensional ME flow models, incorporating different methods of flow separation point prediction, were compared. For two models, determination of the flow separation point was based on fixed ratios of the glottal area at separation to the minimum glottal area; for the third model, the separation point determination was based on fluid mechanics boundary layer theory. Results of flow rate, separation point, and intraglottal pressure distribution were compared with those of an unsteady, two-dimensional, finite element Navier-Stokes model. Cases were considered with a rigid glottal profile as well as with a vibrating vocal fold. For small glottal widths, the three ME flow models yielded good predictions of flow rate and intraglottal pressure distribution, but poor predictions of separation location. For larger orifice widths, the ME models were poor predictors of flow rate and intraglottal pressure, but they satisfactorily predicted separation location. For the vibrating vocal fold case, all models resulted in similar predictions of mean intraglottal pressure, maximum orifice area, and vibration frequency, but vastly different predictions of separation location and maximum flow rate.

Binomial Distribution↗
PubMed2006

The number distribution for involved lymph nodes in cancer.

The number of involved lymph nodes exhibits considerable heterogeneity within populations. Here, the implications of population heterogeneity are explored with respect to the kinematics of nodal metastases. Data from the National Cancer Institute's Surveillance, Epidemiology, and End Results program for 224656 breast, 12404 gastric, 18015 rectal, 4117 cervical and 2443 laryngeal cancers as well as 9118 melanomas were used to construct frequency distributions for the number of involved nodes which were then fitted to the negative binomial distribution. The negative binomial distribution described the heterogeneity in nodal involvement well. The patterns of nodal involvement can be explained by either of two models: one where involved nodes could seed further nodal metastases, the other where the number of nodal metastases in any individual was randomly distributed, with the deviations between patients accounted for by population heterogeneity. Since the number of sampled nodes similarly approximated a negative binomial distribution, random involvement with superimposed population heterogeneity would more credibly explain both sets of observations.

Binomial Distribution↗