This study uses simulation techniques to examine the statistical power of the group- randomized design and the matched-pair (MP) randomized block design under various parameter combinations. Both nearest neighbor matching and random matching are used for the MP design. The power of each design for any parameter combination was calculated from 1,000 simulated datasets. The random pair effect HLM model "with" and "without" covariance adjustment, and the fixed pair effect HLM model "with" and "without" covariance adjustment were used to analyze the data from the matched-pair design, and the HLM with covariance adjustment was used to analyze the data from the completely randomized cluster design. Models Used to Generate Data at Stage 1 is appended. (Contains 4 tables and 1 figure.)