Cross-Sectional versus Longitudinal Survey Research: Concepts, Findings, and Guidelines

Abstract

Marketing academics and practitioners frequently employ crosssectional surveys. In recent years, editors, reviewers, and authors have expressed increasing concern about the validity of this approach. These validity concerns center on reducing common method variance bias and enhancing causal inferences. Longitudinal data collection is commonly offered as a solution to these problems. In this article, the authors conceptually examine the role of longitudinal surveys in addressing these validity concerns. Then, they provide an illustrative comparison of the validity of cross-sectional versus longitudinal surveys using two data sets and a Monte Carlo simulation. The conceptualization and findings suggest that under certain conditions, the results from cross-sectional data exhibit validity comparable to the results obtained from longitudinal data. This article concludes by offering a set of guidelines to assist researchers in deciding whether to employ a longitudinal survey approach.

Heritage tourism, CSR and the role of employee environmental behaviour

“…This also helps to reduce the issue of common method variance (CMV), which is highlighted as an issue in cross-sectional survey research (Rindfleisch, Malter, Ganesan, & Moorman, 2008). Moreover, the longitudinal nature of this study has enabled it to overcome some sources of common method biases, such as the measurement context effects (Podsakoff, MacKenzie & Podsakoff, 2003).…”

Strategic goal accomplishment in export ventures: the role of capabilities, knowledge, and environment

“…To limit potential problems associated with common method bias and causal inference, we used a longitudinal research design (Rindfleisch et al 2008). 4 Specifically, we collected data on export venture strategic goals (i.e., cost and differentiation), architectural capabilities (i.e., planning and implementation), degree of internationalization, and export market characteristics (market dynamism and competitive intensity) at t1 and on export venture realized strategy (i.e., realized cost and differentiation advantages) and performance 12 months later (t2).…”

Is “strategy” a dirty word?

“…For example, of great lament to many strategy scholars who were trained in survey methodology, the days are long gone of collecting data via a single cross-sectional survey, analyzing the results via SEM, and receiving a positive response from the editorial team of a strong journal. Many survey-based studies can be appropriately criticized for common source concerns, inability to empirically demonstrate causality, nested data concerns, and haphazardly constructed models that fit the data decently but do not demonstrate their superiority over equally plausible alternative models (see Rindfleisch et al 2008 for an excellent discussion of these issues and potential paths forward for the survey researcher).…”

“…In fact, if other research approaches provide the evidence that surveys are poorly suited to provide (e.g., secondary data provides substantive evidence and experiments provide causal evidence), surveys are particularly well-suited for testing nomological networks (via structural equations models). 2 Scholars who use surveys have, over time, improved their approaches to confront some of the common criticisms of survey research with improved design, such as reducing common source concern by collecting dependent variables from different sources (e.g., Podsakoff et al 2003) or by providing suggestive evidence of causality via longitudinal design (e.g., Rindfleisch et al 2008). Concerns can also be addressed through analysis strategies, such as using methods that parcel out variance due to interdependencies (e.g., hierarchical linear modeling), including a common method factor in models, or empirically comparing the fit of a model to theoretically reasonable rival models.…”