Confidence Intervals for Successive Comparisons of Ordered Treatment Effects

present a new procedure for making successive comparisons between ordered treatments. Their procedure has important applications for problems where the treatments can be assumed to satisfy a simple ordering, such as for a sequence of increasing dose-levels of a drug. The advantage of their procedure is that it provides more chance to detect when changes in the treatment means occur than other test procedures (for example: test in Hayter\ucite4). The disadvantage of their procedure is that it is not as powerful as other test procedures. In this paper we propose a test procedure which try to keep the advantage of Lee and Spurrier's procedure and promote the power performance of their test procedure.