Market research suppliers want to provide a differentiated product or service offering to their clients. However, the frequent need to appear ‘new’ results in adaptation of research to different contexts. This has consequences for validity. In this paper we make the case for tempering the existing enthusiasm for constant ‘innovation’ in market research methodologies. In particular, we argue that unfettered adaptation can lead to the generation of invalid findings. We demonstrate some methods of how invalid results can develop. Finally we explain current concepts of ‘validity’ and provide an innovative way of showing the relationship between the dozen or more varieties of validity that are commonly used in the literature(s). This paper aims to remind practitioners and academics alike, that concepts of validity are important and that there is no point in having a perfectly reliable, but completely invalid, measurement tool.