本文中，依據Hollander和Pe na’s(1992)對於設限資料所提出的適合度檢定，我們推導截取資料下的模式適合度檢定。檢定統計量為Wald型式且在虛擬假設下其漸近分配為卡方分配。模擬結果顯示在截取比例不大的情況下，該檢定可以達到正確的顯著水準。 In this article, procedures analogous to Hollander and Pe˜na’s goodness-of-fit test for censored data are developed under random truncation model. This leads to the development of an asymptotic test based on a Wald-type statistic with a chi-squared limiting null distribution. The general conclusions from the simulation study are that the proposed test usually achieves the desired signifcance levels when the probability of truncation is not too large.
