The Estimation And Test In Gee Method When PA Condition Is Volidated

Reliable trial was used to research and develop new products, and also produce new manufactures in a large scale. Generally speaking, it cost much time and money in Reli-abe trial. In many cases we don't allow everything in the trial to loss efficacy, so it can appear many truncated data. Namely, in the trial something is fine while other is inactive. No degrees of freedom left to estimate the error variance when the data of this design are analyzed, so the standard ANOVA can't be used. Therefore, it's vital important to investigate some methods of analyzing unreplicated factorial designs of some experiment indexes which obey truncated normal distribution. This paper studies five representative methods of analyzing saturated unreplicated factorial designs on identifying active contrasts and their tests performance when the experiment indexes are from truncated normal distribution.