Educational games have become an established paradigm of instructional practice; however, there is still much to be learned about how to design games to be the most beneficial for learners. An important consideration when designing an educational game is whether there is good alignment between its content goals and the instructional behaviors it makes in order to reinforce those goals. Existing methods for measuring alignment are labor intensive and use complex auditing procedures, making it difficult to define and evaluate this alignment in order to guide the educational game design process. This thesis explores a way to operationalize this concept of alignment and demonstrates an analysis technique that can help educational game designers to both measure the alignment of current educational game designs and predict the alignment of prototypes of future iterations. In my work, I explore the use of Replay Analysis, a novel technique that uses in-game replays of player sessions as a data source to support analysis. This method can be used to capture gameplay experience for the evaluation of alignment, as well as other forms of analysis. The majority of this work has been performed in the context of RumbleBlocks, an educational game that teaches basic structural stability and balance concepts to young children. Using Replay Analysis, I leveraged replay data during a formative evaluation of RumbleBlocks to highlight some misalignments the game likely possesses in how it teaches some concepts of stability to players. These results led to suggestions for several design iterations. Through exploring these design iterations, I further demonstrate an extension of Replay Analysis called Projective Replay Analysis, which uses recorded student replay data in prototypes of new versions of a game to predict whether the new version would be an improvement. I implemented two forms of Projective Replay: Literal Projective Replay, which uses a naïve player model that replays past player actions through a new game version exactly as they were originally recorded; and Flexible Projective Replay, which augments the process with an AI player model that uses prior player actions as training data to learn to play through a new game. To assess the validity of this method of game evaluation, I performed a new replication study of the original formative evaluation to validate whether the conclusions reached through virtual methods would agree with those reached in a normal playtesting paradigm. Ultimately, my findings were that Literal Projective Replay was able to predict a new and unanticipated misalignment with the game, but Flexible Projective Replay, as currently implemented, has limitations in its ability to explore new game spaces. This work makes contributions to the fields of human-computer interaction by exploring the benefits and limitations of different replay paradigms for the evaluation of interactive systems; learning sciences by establishing a novel operationalization of alignment for instructional moves; and educational game design by providing a model for using Projective Replay Analysis to guide the iterative development of an educational game.