本文是探討用Durbin-Watson(1950)的統計量來檢定殘差之間的獨立性假設,統計模型有一個假設,就是殘差的獨立性假設,每個殘差彼此之間是獨立的,觀察值之間彼此不會互相影響,若違反此假設,估計量會缺乏效率性。 Durbin-Watson在1950年發表了一篇論文,但因為此篇論文的定理及證明很深奧,本研究為了讓讀者能更深入了解定理的精隨,所以此篇論文將定理拆成很多小性質,以及更深入的推論。 This article is to use Durbin-Watson(1950)statistic to test the assumption of independence between the residuals. The statistical model has a hypothetical is assumption of independence of the residuals. Every residual is independent of each other. Observations do not affect each other. If violation of this assumption, estimator will be inefficient. Durbin-Watson(1950)wrote a paper in 1950, but as the theorems of the thesis and proof are deep. In this study, in order to give readers a better understanding of these theorems so these theorems are split into many small details as well as more in-depth inferences.