2005 | OriginalPaper | Chapter
Repeated Confidence Intervals in Self-Organizing Studies
Authors : Joachim Hartung, Guido Knapp
Published in: Data Analysis and Decision Support
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
By using the generalized inverse chi-square method of transforming p-values in self-organizing studies as introduced by Hartung and Knapp (2003), one can construct a two-sided confidence interval for the parameter of interest after each realized sequential stage. Provided that in each sequential stage an unbiased estimate of the parameter of interest is available, the repeated confidence intervals always hold the nominal confidence level even in case of early stopping the trial. Moreover, the repeated confidence intervals are always nested, that is, an interval calculated after a performed stage is completely included in all the previous calculated intervals. The use of p-values in the present approach allows the calculation of confidence intervals for various parameters given a suitable test statistic and an unbiased estimate in each sequential stage.