{"title":"Sample size recommendation for a bioequivalent study","authors":"C. Bhupathi, Venakata HaraGopal Vajjha","doi":"10.6092/ISSN.1973-2201/6699","DOIUrl":null,"url":null,"abstract":"There are clear guidelines and suggestions on the sample size and power calculation from health authorities (HA) for Bio equivalence (BE) studies in Healthy volunteers (HV). The suggested power is at least 80\\% and type 1 error is 5\\%. In real life situations, the clinical trials plan with more than 80\\%, giving rise to larger sample size. The increased power means more subjects, more wastage of time and more resources to complete the study, resulting in more money spent. This paper attempts to show how much reduction in the sample size can be achieved without affecting the scientific validity of the study and also the brief summary on the overall effect of reduced sample size on resources (subjects, time, blood and cost). We executed simulations in order to show the impact on the power and the 2 one sided confidence interval approach to show the study equivalence or otherwise. For illustration purpose, a couple of 2 period cross over studies were considered. 100 simulations were executed with different sample sizes to compare with the original results.","PeriodicalId":45117,"journal":{"name":"Statistica","volume":null,"pages":null},"PeriodicalIF":1.6000,"publicationDate":"2017-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Statistica","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.6092/ISSN.1973-2201/6699","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"STATISTICS & PROBABILITY","Score":null,"Total":0}
引用次数: 6
Abstract
There are clear guidelines and suggestions on the sample size and power calculation from health authorities (HA) for Bio equivalence (BE) studies in Healthy volunteers (HV). The suggested power is at least 80\% and type 1 error is 5\%. In real life situations, the clinical trials plan with more than 80\%, giving rise to larger sample size. The increased power means more subjects, more wastage of time and more resources to complete the study, resulting in more money spent. This paper attempts to show how much reduction in the sample size can be achieved without affecting the scientific validity of the study and also the brief summary on the overall effect of reduced sample size on resources (subjects, time, blood and cost). We executed simulations in order to show the impact on the power and the 2 one sided confidence interval approach to show the study equivalence or otherwise. For illustration purpose, a couple of 2 period cross over studies were considered. 100 simulations were executed with different sample sizes to compare with the original results.