Many statistical methods currently employed  to evaluate the effect of a  marketing campaign in dealing with observational data advocate strong parametric assumptions to correct for endogeneity among the participants.  In addition, the assumptions compromise the estimated values when applied to  data in which the research expects endogeneity but this is not realized. Based on the recent advances in the literature of causal models dealing with data collected across time, we propose a dynamic version of  the inverse-probability-of-treatment weighting within the latent Markov model. The proposal, which is based on a weighted maximum likelihood approach, accounts for endogeneity without imposing strong restrictions. The likelihood function is maximized through the Expectation-Maximization algorithm which is suitably modified to account for the inverse probability weights.   Standard errors for the parameters estimates are obtained by a nonparametric bootstrap method. We show the  effects of multiple mail campaigns conducted by a large European bank with the purpose to influence their customers to the  acquisitions of the addressed financial products.