An increasing number of articles in marketing as well as in related fields such as international business, supply chain management, and operations management have recently pointed to issues associated with endogeneity (Guide & Ketokivi, 2015; Jean, Deng, Kim, & Yuan, 2016; Shugan, 2004). Endogeneity constitutes a critical problem for research as it compromises key conditions for claiming causality (Antonakis, Bendahan, Jacquart, & Lalive, 2010, 2014) and both the direction and the size of its bias are difficult to predict in advance (Hamilton & Nickerson, 2003). A failure to consider and correct for endogeneity in research practice can lead to biased and inaccurate results, and poses the risk of drawing incorrect conclusions about cause and effect relationships between concepts of interest. Even though the issue is much more predominant in naturally occurring data (e.g. regularly and automatically collected customer data at the point of purchase or via web browsing) as opposed to market research data (e.g. data collected through survey questionnaires), and is less of a problem for experimental data (e.g. Anderson & Simester, 2004), any study involving questionnaire or survey design is potentially subject to endogeneity bias (Toubia, Simester, Hauser, & Dahan, 2003). Endogeneity is most commonly described in the context of ordinary least squares (OLS) estimation, and refers to a situation in which an independent (explanatory) variable correlates with the structural error term (also referred to as ‘disturbance term’ or ‘residual’) in a model (Kennedy, 2008; Wooldridge, 2002). In such a situation, the error term is not random and the estimation is inconsistent, which implies that the coefficient estimate of the independent variable fails to converge to the true value of the coefficient in the population as sample size increases. When an independent variable correlates with the error term, the coefficient estimate includes the effect of the respective independent variable on the dependent variable as well as the effects of all unobserved factors that correlate with the independent variable and explain the dependent variable, thus rendering its interpretation problematic, or even useless (Antonakis et al., 2010, 2014). If this correlation is ignored, the estimated effect of the observed variable is likely to be biased. This bias is referred to as the endogeneity bias (Chintagunta, Erdem, Rossi, & Wedel, 2006). Endogeneity is a major concern in many areas of marketing and related research, which rely on employing regression-based analyses with the aim to draw causal inferences (Jean et al., 2016). In essence, endogeneity may affect the causal inferences that researchers make with regard to the hypothesized associations between variables, and failure to account for this may lead to spurious findings resulting in misleading theoretical as well as managerial implications (Semadeni, Withers, & Certo, 2014). Against this background, editors and reviewers of various disciplines in the area of management studies increasingly point to endogeneity as a likely alternative explanation for results provided in manuscripts they process, and therefore endogeneity considerations become more and more of a (contributing) reason for manuscript rejection (e.g. Guide & Ketokivi, 2015; Larcker & Rusticus, 2010; Shugan, 2004). In spite of the fact that several approaches to address endogeneity have been available for almost three decades, only fairly recently have some of these remedies been applied in studies published in marketing journals (Hamilton & Nickerson, 2003), and the number of researchers proactively correcting for endogeneity still remains very low.