This study aims to evaluate the level of reproducibility of the marketing field. The research is motivated because many significant published research findings in various scientific areas, including marketing, have been found to be false or only partially replicable, a phenomenon labelled Reproducibility Crisis. This crisis is partly due to the strong overreliance on frequentist statistics and the misuse and misinterpretation of p-values in the Null Hypothesis Significance Testing (NHST) framework. This study offers two main contributions: first, it develops a methodological, quantitative evaluation of the most-cited published papers in marketing history in its four top journals, creating an overall index of marketing science reproducibility. Second, it analyzes how misuse and misinterpretation of p-values and frequentist statistics have undermined marketing science's reproducibility and discusses possible solutions for these problems. We selected a representative sample of the marketing literature, screening the papers using hierarchical classification criteria and the Web of Science (WoS) database to select the most-cited papers.