No abstract

No abstract

Standard statistical analysis of variance has been used on data from weekly determinations of 15 blood constituents in each of 68 normal subjects, our purpose being to isolate and estimate biological components of observed variation. These components include intra-individual, or "personal" variation, and inter-individual, or "group" variation. The most critical problem, that of separating personal variation from long-term analytic deviations in each individual's data record, was resolved with the aid of concurrent analysis of a constant "pooled" serum. Comparison of isolated personal variation with inter-individual variation indicates that many common blood tests—e.g., magnesium, calcium, total protein, uric acid, serum enzymes, and cholesterol—could contribute to an individually distinctive blood "profile" if substantial improvements were made in analytic precision. Presently, only cholesterol (among older women) and uric acid (in males) appear to possess strong capabilities for distinguishing among normal individuals.

JSTOR is a not-for-profit service that helps scholars, researchers, and students discover, use, and build upon a wide range of content in a trusted digital archive. We use information technology and tools to increase productivity and facilitate new forms of scholarship. For more information about JSTOR, please contact support@jstor.org.. Biometrika Trust is collaborating with JSTOR to digitize, preserve and extend access to Biometrika. SUMMARY A method is developed for constructing a confidence band for a cumulative distribution function with known functional form. The band is derived using the maximum absolute difference between the true function and an estimator of it. The normal distribution with unknown mean and variance is treated in detail. The band derived in this case is found to be superior in certain instances to the one due to Kanofsky (1968a) with respect to the expected band width at selected points, and the expected maximum band width.