We develop a model of customer channel migration and apply it to a retailer that markets over the Web and through catalogs. The model (1) identifies the key phenomena required to analyze customer migration, (2) shows how these phenomena can be modeled, and (3) develops an approach for estimating the model. The methodology is unique in its ability to accommodate heterogeneous customer responses to a large number of distinct marketing communications in a dynamic context. Results indicate that (1) Web purchasing is associated with lower subsequent purchase volumes relative to buying from other outlets, (2) marketing efforts are associated with channel usage and purchase incidence, offsetting negative Web experience effects, and (3) negative interactions occur between like communications (catalog/catalog or email/email) as well as between different types of communications (catalog/email). We further find that, over the four-year period of our data, a Web-oriented "migration" segment emerged, and this group had higher sales volume. Our post hoc analysis suggests that marketing efforts and exogenous customer level trends played key roles in forming these segments. We rule out alternative explanations such as that the Web attracted customers who were already heavy users, or that the Web developed these customers into heavier users. We conclude with a discussion of implications both for academics and practitioners.