Sample size re-estimation is the pre-planned recalculation of the required number of evaluable participants during an ongoing clinical trial. It responds to uncertainty in parameters of the original planning, such as variance, event rate, or the proportion of evaluable subjects. Unlike sample size planning before trial initiation, it is performed after an interim analysis and must be designed to preserve the error probability of the confirmatory conclusion. <\/p>\n
The original sample size is based on assumptions that are often only verifiable to a limited extent before the trial begins. For a binary or time-to-event endpoint, the observed frequency may differ substantially from the predicted one; for continuous endpoints, the variability may differ from expectations. An adjustment can then bring the amount of information back in line with the scientific question, rather than continuing a trial with insufficient precision or power. <\/p>\n
The adjustment is not synonymous with increasing the sample size after a disappointing effect. A re-estimation of nuisance parameters based on blinded data differs methodologically from a decision that uses the observed treatment effect. The more comparative efficacy information enters the adjustment, the more carefully bias, error control, and the confidentiality of interim results must be handled. An exclusively blinded re-estimation of variability or event rate has practically only a minor impact on the Type I error rate and is therefore assessed differently by regulators than an adjustment based on the observed treatment effect, for which explicit assurance of error control must be provided. <\/p>\n
The adaptive plan describes the data basis for the recalculation, the timing or information fraction, the permissible range of the new sample size, and the rule for its implementation. It also specifies whether the original hypothesis, endpoint, and primary analysis remain unchanged. A sample size re-estimation must not serve as an occasion to change the objective in light of the interim results. <\/p>\n
In an unblinded re-estimation, the final analysis must account for the adaptivity introduced by the decision. Simulations can demonstrate in advance how different actual variances, event rates, or effects affect Type I error, power, and estimation quality. The result of the interim analysis does not belong in routine trial operations if individuals with recruitment or data decisions could thereby gain knowledge of the effect. <\/p>\n
In event-driven trials, the adjustment may refer to the target number of events rather than the number of recruited subjects. Lower event rates then not only prolong recruitment but also change the time to the intended information. The planning rule must distinguish whether additional participants, longer follow-up, or a higher number of events are permissible. Each of these measures may have different consequences for feasibility, data maturity, and the currency of standard therapy. <\/p>\n
A maximum sample size limits how far the trial may grow based on the re-estimation. Without such a limit, costs, duration, and exposure can increase substantially, even though the scientific question remains unchanged. <\/p>\n
Sample size, sample size justification, and power calculation describe the justification of trial size before recruitment. Sample size re-estimation, in contrast, is a prospectively anchored procedure within the trial protocol. It does not replace the original justification but specifies under which data conditions and by which method a limited reassessment may occur. <\/p>\n
A post-hoc extension due to slow recruitment is also not automatically a sample size re-estimation. More time or more centers do not necessarily change the analytically required amount of information. The term refers to the adjustment of the number of participants or events based on a statistical rule, not every operational change to the recruitment plan. <\/p>\n
Practical implementation requires a clear separation of data cut-off, statistical calculation, and recruitment control. If the target number changes, centers, supply quantities, budget, and visit capacity must be adjusted without confidential effect information reaching the operational teams. For regulatory communication, it must be documented in a traceable manner whether the change was within the approved adaptive rule or triggers a substantial protocol amendment. <\/p>\n
Full-service CROs such as Mediconomics support the simulation and description of the re-estimation rule, establish data provision for a secure interim cut-off, manage the expansion of centers and investigational product logistics after the decision, and document the adjustment including its consequences for analysis, timeline, and clinical study report.<\/p>\n
Can a sample size re-estimation arbitrarily replace the original effect assumption?<\/strong><\/p>\n No. The permissible adjustment and the information used must be defined in advance. A post-hoc selection of a more favorable assumption would jeopardize the confirmatory interpretation. <\/p>\n Is a blinded variance estimation always risk-free?<\/strong><\/p>\n It does not use treatment assignment and is therefore assessed differently than an unblinded adjustment. Nevertheless, the timing, method, and its compatibility with the endpoint and analysis plan must be established in advance. <\/p>\n Does the primary analysis automatically change with more participants?<\/strong><\/p>\n No. In a planned adaptation, the primary question often remains unchanged. However, the final analysis must correctly account for the adjustment specified in the design and its error control. <\/p>\n Sample size re-estimation is the pre-planned recalculation of the required number of evaluable participants during an ongoing clinical trial. It responds to uncertainty in parameters of the original planning, such as variance, event rate, or the proportion of evaluable subjects. Unlike sample size planning before trial initiation, it is performed after an interim analysis and […]<\/p>\n","protected":false},"author":10,"featured_media":0,"parent":0,"template":"","meta":{"_acf_changed":false,"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"glossary-cat":[22],"class_list":["post-7818","glossary","type-glossary","status-publish","hentry","glossary-cat-biostatistik-methodik"],"acf":[],"related_terms":"","external_url":"","internal_reference_id":"","_links":{"self":[{"href":"https:\/\/mediconomics.com\/en\/wp-json\/wp\/v2\/glossary\/7818","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mediconomics.com\/en\/wp-json\/wp\/v2\/glossary"}],"about":[{"href":"https:\/\/mediconomics.com\/en\/wp-json\/wp\/v2\/types\/glossary"}],"author":[{"embeddable":true,"href":"https:\/\/mediconomics.com\/en\/wp-json\/wp\/v2\/users\/10"}],"version-history":[{"count":0,"href":"https:\/\/mediconomics.com\/en\/wp-json\/wp\/v2\/glossary\/7818\/revisions"}],"wp:attachment":[{"href":"https:\/\/mediconomics.com\/en\/wp-json\/wp\/v2\/media?parent=7818"}],"wp:term":[{"taxonomy":"glossary-cat","embeddable":true,"href":"https:\/\/mediconomics.com\/en\/wp-json\/wp\/v2\/glossary-cat?post=7818"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}Regulatory References<\/h2>\n
\n