The sample size calculation was based on the proportion of fully vaccinated children aged 0 to 23 months. We assumed that the pre-intervention proportion of fully vaccinated children was 53% [5] and we wished to detect a change of 10% (i.e. 63% fully vaccinated children post-intervention) with at least 80% power and a 5% significance level. We set the variation between LGA to a value of k (the standard deviation divided by the mean) of 0.18 based on available data on the mean coverage of Pentavalent 3 from routine vaccine records in the study setting. The same value of k was assumed for the variation between Wards and villages. We also allowed for a non-response of 15%. The sample size was determined using a simulation written in R which allowed for the clustering in the sample and the regression analysis. Specifying four Wards per LGA, three villages per Ward and 25 children per village, the smallest number of LGA which gave at least 80% power was four per arm. This gave a total of 1200 children per study arm per survey.

Note: The content above has been extracted from a research article, so it may not display correctly.

Please log in to submit your questions online.
Your question will be posted on the Bio-101 website. We will send your questions to the authors of this protocol and Bio-protocol community members who are experienced with this method. you will be informed using the email address associated with your Bio-protocol account.

We use cookies on this site to enhance your user experience. By using our website, you are agreeing to allow the storage of cookies on your computer.