共變異數分析下處理均差精確信賴區間之樣本數計算

Abstract

對於共變異數分析下的處理均差，本研究提供了精確信賴區間兩個原則的樣本數計算。在計算樣本數時，利用信賴區間的方法可以提供更多參數的資訊，通常會希望信賴區間寬度越狹窄越好，因此可以透過樣本數的決定來獲得狹窄的信賴區間，以預期參數的估計擁有高度的準確度。共變異數分析下處理均差的信賴區間寬度決定於處理均差的標準差，而此標準差與t分配及卡方分配有關，透過統計分配性質的嚴謹討論，針對不同參數組合下，計算達到信賴水準所需要的最適樣本數。

This article provides the sample size calculation for precise confidence interval of mean difference of treatment for analysis of covariance (ANCOVA). Calculating appropriate sample size with the approach of confidence interval could provide more information for population. The adoption of the sample size could narrow confidence interval, and the estimation accuracy of the population was expected to be high. The standard deviation decided confidence interval width of mean difference of treatment for ANCOVA which is related to T statistic and Chi-Square statistic. Thus, using these T statistic and Chi-Square statistic to calculate a proper sample size with different combination of population under required confidence level.