This report compares the use of continuous and group statistical analysis for prospective post-market vaccine and drug safety surveillance based on observational electronic health data. The comparison focuses on 1) type 1 error, 2) statistical power, 3) the expected time to signal when the null hypothesis is rejected, and 4) the sample size required to end surveillance without rejecting the null.
If you are using a web page screen reader and are unable to access this document, please contact the Sentinel Operations Center for assistance by clicking on the Submit Comments link above or sending an email requesting assistance to email@example.com.
Ivair R. Silva, PhD; Department of Population Medicine, Harvard Pilgrim Health Care Institute and Harvard Medical School, Boston, MA and Department of Statistics, Universidade Federal de Ouro Preto, Ouro Preto, Minas Gerais, Brazil
Martin Kulldorff, PhD; Department of Population Medicine, Harvard Pilgrim Health Care Institute and Harvard Medical School, Boston, MA