SAMPLE SIZE DETERMINATION IN HEALTH STUDIES A Practical Manual S. K. Lwanga Epidemiological and wi and S. Lemeshow World Health Organization Geneva 1991WHO Library Cataloguing in Publication Data Langa. S. ‘Semple size determination in health studies a practical manual 1 Sampling studies 2 Health surveys LLameshow. S. lutte ISBN 92 4 154408 8 (NLM Classification: WA 850) (© World Heath Organization 1991 Pubteations of the Wort Hen Oganzation enioy copyright protection a acconanee wth the provisions af rote of he Universe! Copynght Convention. Fer rats of reproduction oF ‘vanetion of WHO publestors. In pr oF Infra. sppseaton ‘oud te made tothe Otfoe of Publestons, Wora Heath Drgenzaton, Geneva, Surzean. The Worl Heath Organiza ton eleames such applications “Tha designate employed athe rsertation ofthe mstriin th pubiaton do not imply the expression of any opinion ‘whateowar on the part ofthe Secretariat ofthe Word Heath Drgatiznioncorcering the aga satscf ary county tery, ‘yo ata orf satan er canning tection oF ‘The manton of specie compares f ean manufactures prodts does nt mpl that they ae endorsed ox ecommenad by ihe World Health Organation in petarnce fo ttre of Similar nature that ate not mentioned £401 ahd omissions rented he vars of propel products ae asingushed by lena copra lene “ear lon te esos forthe waws expr nts publeatonContents Preface Introduction ‘One-sample situations Estimating a population proportion with specified absolute precision Estimating a population proportion with specified relative precision Hypothesis tests for a population proportion ‘Two-sample situations Estimating the difference between two population proportions with specified absolute precision Hypothesis tests for two population proportions Case-contral studies Estimating an odds ratio with specified relative precision ‘Hypothesis tests for an odds ratio Cohort studies Estimating a relative risk with specified relative precision Hypothesis tests for a relative risk ‘Lot quality assurance sampling ‘Accepting a population prevalence as not exceeding a specified value Decision rule for “rejecting a lot” Incidence-rate studies Estimating an incidence rate with specified relative precision Hypothesis tests for an incidence rate Hypothesis tests for two incidence rates in follow-up (cohort) studies Definit ns of commonly used terms ‘Tables of minimum sample size 1. Estimating a population proportion with specified absolute precision 2. Estimating a population proportion with specified relative precision 3. Hypothesis tests for a population proportion imating the difference between two population propor~ tions with specified absolute precision 7 7 18 2 25 n 3