Session 450

Looking for Truth--Curves in Research

Track R

Date: Tuesday, September 23, 2014

 

Time: 17:15 – 18:30

Paper

Room: Malta


Session Chair:

  • Jay Horwitz, Bocconi University

Title: A Reanalysis of Partial Least Squares Studies in Strategic Management Journal

Authors

  • Mikko Rönkkö, Aalto University

Abstract: The Partial Least Squares (PLS) method has seen increasing use in the strategic management research community in the recent years and Strategic Management Journal (SMJ) has become one of the journals publishing management papers using the method. At the same time, there is an emerging controversy caused by recent challenges to the use of the method claiming not only that the method does not provide the advantages that the proponents claim, but that it is altogether unsuitable for the purpose of theory testing that it is currently used for. I reanalyze 14 papers from SMJ that use the PLS method. The reanalysis shows that the way that the method is used cannot detect model misspecification and hence cannot be used as model test.

Title: Dangerous Curves: How “Curvilinear” Relationships May Impede Theory Development?

Authors

  • Hanko Zeitzmann, Zayed University
  • Donald Hatfield, Virginia Tech

Abstract: Many empirical studies in strategic management report curvilinear relationships between independent and dependent variables. We encourage authors to see curvilinear relationships as the starting point for deeper, more thorough investigations. We argue curvilinear relationships are not the final answer to the questions we pose in our research, although researchers generally stop their investigations when they find a statistically significant curvilinear relationship. To improve theory development and managerial understanding, the causes of curvilinear findings need to be disentangled—by examining if they are the result of combined populations, ignored outliers, or merged opposing constructs that appear as a “curvilinear” macro-construct. We posit that curvilinear results raise more questions than they provide answers.

Title: The Effect of Boundary Permeability Across New Venture Growth Dimensions

Authors

  • Robert Nason, Syracuse University
  • Johan Wiklund, Syracuse University
  • Alexander McKelvie, Syracuse University

Abstract: Boundary research has been dominated by theory predicting how firms set the location of boundaries by efficiently allocating accumulated resources. We focus on how firms alter the nature of boundaries through resource accumulation strategies aimed at creating value. Specifically, we develop the concept of boundary permeability to refer to the extent to which firms utilize resources which remain outside of organizational borders. We contextualize the permeability decision in the new venture context and explore the tension between access to critical resources and limited control over unowned resources. We link boundary permeability to distinct value creating dimensions of sales, employment, and profitability growth. Using a sample of knowledge-intensive Swedish startups, our results reveal differing linear and curvilinear relationships of boundary permeability across heterogeneous growth dimensions.

Title: Using Semiparametric Regression to Estimate Nonlinear Relationships in Management Research

Authors

  • Jay Horwitz, Bocconi University

Abstract: Management research contains many nonlinear (notably, U-shaped) relations yet the methods we use to test these relationships have serious limitations. This paper aims to close this gap by drawing on advances in semiparametric methods outside the field of management.

All Sessions in Track R...

Sun: 08:00 – 09:15
Session 253: Research Methods and Publishing, and Publishing Research Method Advances
Sun: 11:15 – 12:30
Session 310: Assessing the Broad Impact of Research
Mon: 08:00 – 09:15
Session 448: Looking to the Past--Going toward the Future
Mon: 14:45 – 16:00
Session 395: Beyond the Known Methods--Introduction to Emerging Techniques
Mon: 16:30 – 17:45
Session 369: The Future of Research Methods in Strategic Management Research
Tue: 11:00 – 12:15
Session 397: Beyond the Longitudinal--Panel Analysis
Tue: 17:15 – 18:30
Session 450: Looking for Truth--Curves in Research


Strategic Management Society

Madrid