本文主要討論組可分處理集區設計當同一集區內漏失t個對照處理時之連接穩健性,以及當漏失整個集區時之連接穩健性;並且(1)令屬於不同組別之試驗處理於同集區內一起出現之次數於零的條件下,分別將組可分處理集區設計當同一集區內漏失t個對照處理,以及當漏失整個集區時之效率值確實解出。(2)令屬於同組別之試驗處理於同集區內一起出現之次數為零的條件下,分別將組可分處理集區設計當同一集區內漏失t個對照處理,以及當漏失整個集區時之效率值確實解出。< Robustness of group divisible treatment designs (GDTD) against missing data is investigated under two patterns of missing observations. One of them is when t observations of the control treatment pertaining to one block are missing, and the second one is when all the observations in one block are missing. Two criteria of robustness of designs are considered, the criterion of connectedness, and the criterion of A-efficiency. Robustness of general GDTD's are investigated, and the exact A-efficiencies of GDTD's when .lambda./sub 1/=0 and .lambda./sub 2/=0 are derived, respectively.<
