BACKGROUND AND AIM: There is hope that the bigger the data, the bigger the knowledge will become. Very large data are or will be made available and shall bring robust and replicable effect estimates in exposome research. While larger data and complementary sources of data will, with little doubt, bring robust effect sizes to estimate how environmental, toxic, social, and biological exposures are associated with health outcomes. We may also expect that larger (and precise) data will allow us to go beyond common effects (as an analogy to common genetic variants) and detect rare or small effects. Moving on into the paradigm of big data, it may be wise to remind each other that correlation is not proof of causality. METHODS: Although bigger (observational) data will bring confidence on the strength of some association, relationships in large data are similarly affected by important selection and structural biases, confounding effects, and measurement errors. One strength of the European Human Exposome Network is to bring multiple study designs and dynamic longitudinal analytical strategies to help to triangulate the evidence. RESULTS:We shall, for example, use negative control, quasi-experimental designs, interventions, and instrumental variables (e.g. Mendelian randomization or instrument based on exogenous factors, i.e. environmental policies) to infer causation and identify causative pathways. CONCLUSIONS:These causal designs and approaches however are not always applicable or available. One should also seek for additional ways to gain confidence on the plausibility of causal insights through replication, triangulation, and integration of prior knowledge which is made available in the European Human Exposome Network. KEYWORDS: European Human Exposome Network, Big data, big knowledge, causal insights