How do we go about weighing evidence, testing hypotheses, and making inferences? According to this work, we infer the hypothesis that would, if correct, provide the best explanation of the available evidence. Articulating the model of inference to the best explanation requires an account of what makes one explanation better than another. The author of this treatise distinguishes between the explanation best supported by the evidence - the most likely explanation - and the explanation that would, if true, provide the most understanding. He argues that an illuminating version of inference to the best explanation must rely on the latter notion, and provides an account of what makes one explanation better than another by analyzing the structure of contrastive explanations.