Research Methodology in Strategy and Management: Volume 1

Welcome to the first volume of Research Methodology in Strategy and Management. This book series’ mission is to provide a forum for critique, commentary, and discussion about key research methodology issues in the strategic management field. Strategic management relies on an array of complex methods drawn from various allied disciplines to examine how managers attempt to lead their firms toward success. The field is undergoing a rapid transformation in methodological rigor, and researchers face many new challenges about how to conduct their research and in understanding the implications that are associated with their research choices. For example, as the field progresses, what new methodologies might be best suited for testing the developments in thinking and theorizing? Many long-standing issues remain unresolved as well. What methodological challenges persist as we consider those matters? This book series seeks to bridge the gap between what researchers know and what they need to know about methodology. We seek to provide wisdom, insight and guidance from some of the best methodologists inside and outside the strategic management field. In each volume, renowned scholars will contribute chapters in their areas of methodological expertise.

The field of strategic management has advanced substantially in both theory and empirical research over the last 25 years. However, there are “cracks” beginning to occur in the methodology “dam.” To grow as a discipline, strategic management research must meet and deal effectively with methodological challenges in several areas. We address these challenges in each of the following areas: research questions, data collection, construct measurement, analysis of endogenous relationships, and applications. We present a concise view of the future suggesting ways in which these challenges can be overcome and explain the benefits to the field.

Strategy researchers have become fascinated with the possibilities for developing theoretical perspectives rooted in knowledge and intellectual assets as drivers of superior performance. However, there have been many different schools of thought, each with its own conceptualization lenses and operationalization approaches. In this chapter, we focus on three schools of thought: (1) knowledge as stocks; (2) knowledge as flow; and (3) knowledge as a driver of an organizational capability. We use them to: (a) lay out the distinct approaches to conceptualization and operationalization of strategy-related concepts; and (b) identify specific ways to enhance theory-method correspondence. We believe that considerable progress could be made towards developing a knowledge-based view of strategy but only when accompanied by serious attention to measurement and methodological issues.

In recent years, the network perspective has become highly influential in the strategy research. A number of strategic phenomena and outcomes have been studied successfully by adopting the methodology of social network analysis and taking a relational perspective on firm behavior and outcomes. However, while the social network methodology provides a powerful research tool for strategy researchers, it is fraught with both theoretical and methodological challenges. In this paper, we argue that many of the issues related to using the social network approach in strategy research derive from the use of an essentially individual level methodology being applied to the level of the organization. Organizations being large, complex, and nested entities, the social processes that are implied in network research at the level of the individual are often questionable at the interorganizational level. We identify ten specific issues, grouped under three major heads: issues relating to network structure, to network ties, and to network actors and action. We discuss the theoretical and methodological challenges associated with each issue and conclude with some suggestions for using the network perspective in strategy research.

Research on strategic choices available to the firm are often modeled as a limited number of possible decision outcomes and leads to a discrete limited dependent variable. A limited dependent variable can also arise when values of a continuous dependent variable are partially or wholly unobserved. This chapter discusses the methodological issues associated with such phenomena and the appropriate statistical methods developed to allow for consistent and efficient estimation of models that involve a limited dependent variable. The chapter also provides a road map for selecting the appropriate statistical technique and it offers guidelines for consistent interpretation and reporting of the statistical results.

Longitudinal regression analysis is conducted to clarify causal relations and control for unwanted influences from actor heterogeneity and state dependence on theoretically important coefficient estimates. Because strategic management contains theory on how firms differ and how firm actions are influenced by their current strategic position and recent experiences, consistency of theory and methodology often requires use of longitudinal methods. We describe the theoretical motivation for longitudinal methods and outline some common methods. Based on a survey of recent articles in strategic management, we argue that longitudinal methods are now used more frequently than before, but the use is still inconsistent and insufficiently justified by theoretical or empirical considerations. In particular, strategic management researchers should use dynamic models more often, and should test for the presence of actor effects, autocorrelation, and heteroscedasticity before applying corrections.

The study of strategy is the study of how firms gain and maintain a competitive advantage in the marketplace. It is an examination of both the types of strategy that appear to be most successful in a given situation, as well as the organizational resources, systems, principles, and processes that create, transform, and carry out strategic action in competitive arenas. Since its development as a distinct disciplinary area, strategy research has focused primarily on large, cross-sectional studies of quantitative data gathered through questionnaires, archival sources such as financial reports, and commercial data bases such as PIMS and COMPUSTAT. These analyses have focused on, and revealed, patterns of strategy content, formulation processes, and competitive interaction that exist across firms within a given competitive context and that explain variations in performance across firms. These results have led to the development of several basic theoretical frameworks that help us to understand and predict competitive activity and organizational performance.

Behavioral scientists have long sought to capture how individuals’ understandings, perceptions and beliefs affect their decisions, often through examining the underlying cognitive processes that drive action (Schendel & Hofer, 1979). Economists, for example, are interested in how individuals’ utility functions influence their actions. Marketing researchers investigate how consumers’ preferences are reflected in their purchase behaviors. Organization researchers examine individual characteristics that influence outcomes such as job satisfaction, promotion, and turnover (Aiman-Smith et al., 2002).

This paper considers threats to the internal validity of field studies that utilize survey data. Compared to laboratory experiments and field experiments, field surveys should be strong in realism, practical significance, and normative quality. However, there are substantial threats to internal validity that fall into the general categories of sampling and measurement. We consider these issues and how to deal with them. We pay special attention to the existence and impact of common method variance including strategies for avoiding it, methods for assessing it, and approaches to correcting for it. Our objective is to provide a road map for better use of survey methods.

Strategy researchers typically avoid using data more than a few years old for estimation of cross-sectional models. However, problems that might be caused by older data generally reflect more basic weaknesses in research design. This chapter develops criteria for evaluating the importance of the age of data used in cross-sectional research and indicates ways that better research design may be more effective than the substitution of newer data sets.

In this chapter we ask a simple question: how can we tell if strategic management research is making progress? While other limitations are noted, we argue that it is the absence of metrics for gauging research progress that is most limiting. We propose that research should focus on measures of effect size and that “precision” and “generalizability” in our predictions of important phenomena represent the core metrics that should be used to judge whether progress is occurring. We then discuss how to employ these metrics and examine why existing research practices are likely to hinder efforts to develop cumulative knowledge.

The objective of this chapter is to provide strategy researchers with a general resource for applying structural equation modeling (SEM) in their research. This objective is important for strategy researchers because of their increased use of SEM, the availability of advanced SEM approaches relevant for their substantive interests, and the fact that important technical work on SEM techniques often appear in outlets that may not be not readily accessible. This chapter begins with a presentation of the basics of SEM techniques, followed by a review of recent applications of SEM in strategic management research. We next provide an overview of five types of advanced applications of structural equation modeling and describe how they can be applied to strategic management topics. In a fourth section we discuss technical developments related to model evaluation, mediation, and data requirements. Finally, a summary of recommendations for strategic management researchers using SEM is also provided.

The authors content analyze 76 empirical Strategic Management Journal articles to determine how studies control for threats to internal validity, a common source of flaws in research designs. Results indicate that most studies fail to control for one or more threats to internal validity. In particular, selection effects were the most frequently appearing threat, followed by history effects, ambiguity about the direction of causal inference, changing data sources and subject mortality. In general, the results suggest that strategy researchers need to more carefully account for threats to the internal validity of their research designs. Suggestions for addressing these problems are provided.