Advertisement

Varianz- und kovarianzbasierte Strukturgleichungsmodelle — Ein Leitfaden zu deren Spezifikation, Schätzung und Beurteilung

  • Andreas Herrmann
  • Frank Huber
  • Frank Kressmann
Strukturgleichungsmodelle

Zusammenfassung

Seit Mitte der 80er Jahre gewinnen Strukturgleichungsmodeile in der betriebswirtschaftlichen Forschung an Bedeutung. Jüngste Veröffentlichungen untermauern jedoch deren oftmals fälschliche Anwendung bzw. die Fehlkonzeption des überprüften Modells. Nicht zuletzt erschwert die etablierte, auf kovarianzbasierten Verfahren beruhende Software LISREL die häufig notwendige, jedoch unterlassene Einbindung formativ erfasster Modellkonstrukte. Das varianzbasierte Strukturgleichungsverfahren PLS (partial least squares) weist eine Vielzahl von günstigen Eigenschaften gegenüber kovarianzbasierten Verfahren auf, so auch die problemlose Einbindung formativ erhobener latenter Variablen. Das Hauptargument des Beitrags besteht deshalb darin, einen Leitfaden zur Modellkonzeption, Konstruktoperationalisierung und Auswahl des angemessenen Prüfverfahrens sowie entsprechender Prüfkriterien zu entwickeln, wobei insbesondere die Operationalisierung von nicht beobachtbaren Variablen mittels formativer Indikatoren eine detaillierte Erörterung erfährt.

Kovarianzbasierte Strukturgleichungsmodeile LISREL PLS Varianzbasierte Strukturgleichungsmodeile 

Summary

For twenty years structural equation models have become very popular in economics and business. A review of recent publications shows that these models are very often not properly applied. Especially the spefication of the measurement variables as formative or reflective indicators is not done very carefully. PLS (partial least squares) a covariance based structural equation approach allows formative and reflective indicators. Therefore, the idea, the specification process, and the estimation procedures are discussed.

Keywords

Covariance Based Structural Equation Models LISREL PLS Variance Based Structural Equation Models 

JEL-Classification

C10 M10 M30 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Literatur

  1. Anderson, James C./Gerbing, David W./Hunter, John E. (1987), On the Assessment of Unidimensional Measurement: Internal and External Consistency, and Overall Consistency Criteria, in: Journal of Marketing Research, Vol. 24, November, S. 432–437.CrossRefGoogle Scholar
  2. Anderson, James C./Gerbing, David W. (1991), Predicting the performance of measures in a confirmatory factor analysis with a pretest assessment of their substantive validities, in: Journal of Applied Psychology, Vol. 76, S. 732–740.CrossRefGoogle Scholar
  3. Apel, Heino (1977), Estimation of Soft Models — A Guidance to a Raw Data Input Computerprogram, Philadelphia.Google Scholar
  4. Arnett, Dennis B./Laverie, Debra A./Meiers, Amanda (2003), Developing Parsimonious Retailer Equity Indexes Using Partial Least Squares Analysis: A Method and Applications, in: Journal of Retailing, Vol. 79, S. 161–170.CrossRefGoogle Scholar
  5. Bagozzi, Richard P. (1980), Causal Models in Marketing, New York.Google Scholar
  6. Balderjahn, Ingo (1986), The Robustness of Lisrel Unweighted Least Squares Estimation Against Small Sample Size in Confirmatory Factor Analysis, in: Gaul, Wolfgang/Schrader, Martin (Hrsg.), Classification as a Tool of Research, Amsterdam u.a., S. 3–10.Google Scholar
  7. Bollen, Kenneth A. (1989), Structural Equations with Latent Variables, New York.CrossRefGoogle Scholar
  8. Bollen, Kenneth A./Davis Walter R. (1994), Causal Indicator Models: Identification, Estimation, and Testing, Konferenzbeitrag bei 1993 American Sociological Association Convention, Miami, FL.Google Scholar
  9. Bollen, Kenneth A./Lennox, Richard (1991), Conventional Wisdom on Measurement: A Structural Equation Perspective, in: Psychological Bulletin, Vol. 110, No. 2, S. 305–314.CrossRefGoogle Scholar
  10. Bollen, Kenneth A./Ting, Kwok-fai (2000), A Tetrad Test for Causal Indicators, in: Psychological Methods, Vol. 5, No. 1, S. 3–22.CrossRefGoogle Scholar
  11. Cassel, Claes/Hackl, Peter/Westlund, Anders (1999), Robustness of Partial Least-Squares Method for Estimating Latent Variable Quality Structures, in: Journal of Applied Statistics, Vol. 26, No. 4, S. 435–446.CrossRefGoogle Scholar
  12. Chin, Wynne W. (1995), Partial Least Squares is to LISREL as Principal Components Analysis is to Common Factor Analysis, in: Technology Studies, Vol. 2, S. 315–319.Google Scholar
  13. Chin, Wynne W. (1998a), Issues and Opinions on Structural Equation Modeling, in: MIS Quarterly, Vol. 22, No. 1, S. vii–xviGoogle Scholar
  14. Chin, Wynne W. (1998b), The Partial Least Squares Approach to Structural Equation Modeling, in: Marcoulides, George A. (Hrsg.), Modern Methods for Business Research, Mahwah, NJ, S. 295–336.Google Scholar
  15. Chin, Wynne W./Marcolin, Barbara L./Newsted, Peter R. (1996), A Partial Least Squares Latent Variable Modeling Approach For Measuring Interaction Effects: Results From Monte Carlo Simulation Study and Voice Mail Emotion Adoption Study, Proceedings of the Seventeenth Conference on Information Systems, Cleveland, OH, S. 1–22.Google Scholar
  16. Chin, Wynne W./Newsted, Peter R. (1999), Structural Equation Modeling Analysis With Small Samples Using Partial Least Squares, in: Hoyle, Rick H. (Hrsg.), Strategies for Small Sample Research, Thousand Oaks, CA, S. 307–341.Google Scholar
  17. Churchill, Gilbert A. Jr. (1979), A Paradigm for Developing Better Measures of Marketing Constructs, in: Journal of Marketing, Vol. 16, February, S. 64–73.Google Scholar
  18. Cohen, Jacob (1988), Statistical Power Analysis for the Behavioral Sciences, 2nd edition. Hillsdale, NJ.Google Scholar
  19. Davis, Fiona/Goode, Mark/Mazanec, Josef/Moutinho, Luiz (1999), LISREL and Neural Network Modelling: Two Comparison Studies, in: Journal of Retailing and Consumer Services, Vol. 6, S. 249–261.CrossRefGoogle Scholar
  20. Diamantopoulos, Adamantios (1999), Export Performance Measurement: Reflective Versus Formative Indicators, in: International Marketing Review, Vol. 16, No. 6, S. 444–457.CrossRefGoogle Scholar
  21. Diamantopoulos, Adamantios/Siguaw, Judy A. (2002), Formative vs. Reflective Indicators in Measure Development: Does the Choice of Indicators Matter?, Cornell School of Hotel Administration, working paper.Google Scholar
  22. Diamantopoulos, Adamantios/Winklhofer, Heidi M. (2001), Index Construction with Formative Indicators: An Alternative to Scale Development, in: Journal of Marketing, Vol. 38, May, S. 269–277.Google Scholar
  23. Dijkstra, Theo (1983), Some Comments on Maximum Likelihood and Partial Least Squares Methods, in: Journal of Econometrics, Vol. 22, S. 67–90.CrossRefGoogle Scholar
  24. Edwards, Jeffrey R./Bagozzi, Richard P. (2000), On the Nature and Direction of Relationships Between Constructs and Measures, in: Psychological Methods, Vol. 5, No. 2, S. 155–174.CrossRefGoogle Scholar
  25. Efron, Bradley/Gong, Gail (1983), A Leisurely Look at the Bootstrap, the Jacknife and Cross-Validation, in: The American Statistician, Vol. 37, Issue 1, S. 36–48.Google Scholar
  26. Efron, Bradley/Tibshirani, Robert J. (1993). An Introduction to the Bootstrap, New York.CrossRefGoogle Scholar
  27. Eggert, Andreas/Fassott, Georg (2003), Zur Verwendung formativer und reflektiver Indikatoren in Strukturgleichungsmodellen, in: Kaiserslauterer Schriftenreihe Marketing, Nr. 20, S. 1–24.Google Scholar
  28. Fornell, Claes/Bookstein, Fred L. (1982), Two Structural Equation Models: LISREL and PLS Applied to Consumer Exit-Voice Theory, in: Journal of Marketing Research, Vol. 19, November, S. 440–452.CrossRefGoogle Scholar
  29. Fornell, Claes/Cha, Jaesung (1994), Partial Least Squares, in: Bagozzi, Richard P. (Hrsg.): Advanced Methods of Marekting Research, Cambridge, S. 52–78.Google Scholar
  30. Fornell, Claes/Larcker, David F. (1981), Evaluating Structural Equation Models with Unobservable Variables and Measurement Error, in: Journal of Marketing Research, Vol. 18, February, S. 39–50.CrossRefGoogle Scholar
  31. Fritz, Wolfgang (1995), Marketing-Management und Unternehmenserfolg, 2. Aufl., Stuttgart.Google Scholar
  32. Gefen, David/Straub, Detmar W./Boudreau, Marie-Claude (2000), Structural Equation Models and Regression: Guidelines for Research Practice, in: Communications of the Association for Information Systems, Vol. 4, Article 7, S. 1–79.Google Scholar
  33. Gerbing, David W. (1988), An Updated Paradigm for Scale Development Incorporating Unidimensionality and Its Assessment, in: Journal of Marketing Research, Vol. 25, May, S. 186–192.CrossRefGoogle Scholar
  34. Gerbing, David W./Anderson, James C. (1984), On the Meaning of Within-Factor Correlated Measurement Errors, in: Journal of Consumer Research, Vol. 11, June, S. 572–580.CrossRefGoogle Scholar
  35. Götz, Oliver/Liehr-Gobbers, Kerstin (2004), Analyse von Strukturgleichungsmodellen mit Hilfe der Partial-Least-Squares-Methode, in: Die Betriebswirtschaft, 64. Jg, Heft 6, S. 714–738.Google Scholar
  36. Greene, Vernon L. (1978), Simultaneous Optimization of Factor Accessibility and Representativeness: An Old Solution For a New Problem, in: Psychometrika, Vol. 43, S. 273–275.CrossRefGoogle Scholar
  37. Gujarati, Damodar N. (2003), Basic Econometrics, 4th ed., Burr Ridge, IL.Google Scholar
  38. Hackl, Peter/Westlund, Anders H. (1999), On Structural Equation Modelling For Customer Satisfaction Measurement, in: Total Quality Management, Vol. 11, Nos. 4/5&6, 2000, S. 820–825.CrossRefGoogle Scholar
  39. Hahn, Carsten (2002), Segmentspezifische Kundenzufriedenheitsanalyse, Wiesbaden.CrossRefGoogle Scholar
  40. Hildebrandt, Lutz (1984), Kausalanalytische Validierung in der Marketingforschung, in: Marketing ZfP, Heft 1, S. 41–51.Google Scholar
  41. Homburg, Christian (1992), Die Kausalanalyse — Eine Einführung, in: Wirtschaftswissenschaftliches Studium, Heft 10, S. 499–508.Google Scholar
  42. Homburg, Christian/Baumgartner, Hans (1995), Beurteilung von Kausalmodellen, in: Marketing ZFP, Heft 3, S. 162–176.Google Scholar
  43. Homburg, Christian/Baumgartner, Hans (1996), Applications of Structural Equation Modeling in Marketing and Consumer Research: A Review, in: International Journal of Research in Marketing, Vol. 13, S. 139–161.CrossRefGoogle Scholar
  44. Homburg, Christian/Giering, Annette (1996), Konzeptualisierung und Operationalisierung komplexer Konstrukte, in: Marketing ZFP, Heft 1, S. 5–24.Google Scholar
  45. Hu, Li-tze/Bentler, Peter M. (1999), Cut-off Criteria for Fit Indexes in Covariance Structure Analysis: Conventional Criterias Versus New Alternatives, in: Structural Equation Modelling, Vol. 6, No. 1, S. 1–55.CrossRefGoogle Scholar
  46. Huber, Frank/Herrmann, Andreas/Peter, Sibylle (2003), Ein Ansatz zur Steuerung der Markenstärke, in: Zeitschrift für Betriebswirtschaft, Vol. 73, Nr. 4, S. 345–370.Google Scholar
  47. Hui, B. S./Wold, Herman (1982), Consistency and Consistency at Large of Partial Least Squares Estimates, in: Jöreskog, Karl G./Wold, Herman (Hrsg.), Systems Under Indirect Observation (Teil 2), Amsterdam, S. 119–140.Google Scholar
  48. Hulland, John (1999), Use of Partial Least Squares (PLS) in Strategic Management Research: A Review of Four Recent Studies, in: Strategic Management Journal, Vol. 20, S. 195–204.CrossRefGoogle Scholar
  49. Jarvis, Cheryl Burke/MacKenzie, Scott B./Podsakoff, Philip M. (2003), A Critical Review of Construct Indicators and Measurement Model Misspecifications in Marketing and Consumer Research, in: Journal of Consumer Research, Vol. 30, September, S. 199–218.CrossRefGoogle Scholar
  50. Jöreskog, Karl G. (1978). Structural Analysis of Covariance and Correlation matrices, in: Psychometrika, Vol. 43, S. 443–473.CrossRefGoogle Scholar
  51. Jöreskog, Karl G./Goldberger, Arthur S. (1975), Estimation of a Model with Multiple Indicators and Multiple Causes of a Single Latent Variable, in: Journal of the American Statistical Association, Vol. 10, S. 631–639.Google Scholar
  52. Lohmöller, Jan-Bernd (1989), Latent Path Modeling with Partial Least Squares, Heidelberg. Long, J. Scott (1983): Confirmatory Factor Analysis: A Preface to LISREL, Beverly Hills, CA.Google Scholar
  53. Lyttkens, Eric (1973), The Fixed-Point Method For Estimating Interdependent Systems With the Underlying Model Specification, in: Journal of the Royal Statistical Society, A136, 353–394.CrossRefGoogle Scholar
  54. MacCallum, Robert C./Browne, Michael W. (1993), The Use of Causal Indicators in Covariance Structure Models: Some Practical Issues, in: Psychological Bulletin, Vol. 114, No. 3, S. 533–541.CrossRefGoogle Scholar
  55. McDonald, Roderick P. (1996), Path Analysis with Composite Variables, in: Multivariate Behavioral Research, Vol. 31, No. 2, S. 239–270.CrossRefGoogle Scholar
  56. McDonald, Roderick P./Ho, Moon-Ho Ringo (2002), Principles and Practice in Reporting Structural Equation Analysis, in: Psychological Methods, Vol. 7, No. 1, S. 64–82.CrossRefGoogle Scholar
  57. Mooney, Carl/Duval, Richard D. (1993), Bootstrapping: A nonparametric approach to statistical inference, Thousand Oaks.CrossRefGoogle Scholar
  58. Noonan, Richard/Wold, Herman (1982), PLS Path Modeling with Indirectly Observed: A Comparison of Alternative Estimates For the Latent Variable, in: Jöreskog, Karl/Wold, Herman (Hrsg.), Systems Under Indirect Observation (Teil 2), Amsterdam, S. 75–94.Google Scholar
  59. Rossiter, John (2002), The C-OAR-SE Procedure for Scale Development in Marketing, in: International Journal of Research in Marketing, Vol. 19, S. 305–335.CrossRefGoogle Scholar
  60. Schneeweiß, Hans (1990), Models with Latent Variables: LISREL versus PLS, in: Contemporary Mathematics, Vol. 112, S. 33–40.CrossRefGoogle Scholar
  61. Segars, Albert H. (1997), Assessing the Unidimensionality of Measurement: A Paradigm and Illustration within the Context of Information Systems Research, in: Omega, Vol. 25, No. 1, S. 107–121.CrossRefGoogle Scholar
  62. Steenkamp, Jan-Benedict E. M./van Trijp, Hans C. M. (1991), The Use of LISREL in Validating Marketing Constructs, in: International Journal of Marketing Research, Vol. 8, S. 283–299.CrossRefGoogle Scholar
  63. Steenkamp, Jan-Benedict/Baumgartner, Hans (2000), On the Use of Structural Equation Models for Marketing Modeling, in: International Journal of Marketing Research, Vol. 17, S. 195–202.CrossRefGoogle Scholar
  64. Weber, Robert P. (1982), Content-analytic cultural indicators, Symposium on Cultural Indicators for the Comparative Study of Change, Wien, Harvard.Google Scholar
  65. Wheaton, Blair/Muthen, Bengt/Alwin Duane, Summers Gene (1977), Assessing reliability and stability in panel models, in: Heise, Daniel R. (Hrsg.), Sociological Methodology, San Francisco, S. 84–136.Google Scholar
  66. Williams, Larry J./Edwards, Jeffrey R./Vandenberg, Robert J. (2003), Recent Advances in Causal Modeling Methods for Organizational and Management Research, in: Journal of Management, Vol. 29, No. 6, S. 903–936.CrossRefGoogle Scholar
  67. Winklhofer, Heidi M./Diamantopoulos, Adamantios (2002), Managerial Evaluation of Sales Forecasting Effectiveness: A MIMIC Modeling Approach, in: International Journal of Research in Marketing, Vol. 19, No. 2, S. 151–166.CrossRefGoogle Scholar
  68. Wold, Herman (1980), Model Construction and Evaluation When the Theoretical Knowledge is scarce: Theory and Application of Partial Least Squares, in: Kmenta, Jan/Ramsey, James G. (Hrsg.), Evaluation of Econometric Models, New York, S. 47–74.Google Scholar
  69. Wold, Herman (1982), Soft Modeling: The Basic Design and Some Extensions, in: Jöreskog, Karl G./Wold, Herman (Hrsg.), Systems Under Indirect Observation (Teil 2), Amsterdam, S. 1–54.Google Scholar

Copyright information

© Schmalenbach-Gesellschaft.eV. 2006

Authors and Affiliations

  • Andreas Herrmann
    • 1
  • Frank Huber
    • 2
  • Frank Kressmann
    • 2
  1. 1.Zentrum für Business MetricsUniversität St. GallenSt. GallenSchweiz
  2. 2.Lehrstuhl für Allgemeine Betriebswirtschaftslehre und MarketingUniversität MainzMainzDeutschland

Personalised recommendations