A concept map is a graph model comprised of concepts and undirected links which represent connections between different concepts. It has been widely used in psychology, education, and more recently introduced in marketing. Concept maps have been analysed heuristically or algorithmically until the recent proposal of Hui et al. (2008). They develop a probability model that provides a unified modelling framework for the analysis of concept maps. In this paper we extend this modelling framework in order to make it suitable for testing the empirical evidence of theories or main tenets of these. We identify a theory by a set of core propositions each essentially asserting that one set of independent variables affects one dependent variable. Moreover, every independent/dependent variable can have several operational definitions. Here, data consist of a selected sample of scientific articles from the empirical literature on the theory at issue; each article can include one or more tests of the theory being assessed. Differently from Hui et al., in our adapted version of concept map—that we call tenet map—the links of a map are two-layer: first-layer links connect the variables which have been related in the article at issue, second-layer links represent connections which have been found—consistently with the theory—statistically significant. In addition, either layer matrix of link-formation probabilities is block-symmetric for not all the independent variables can be connected to every dependent variable and each construct is associated with a set of operational definitions solely. Similarly to the original version, observed maps are censored: one form of censoring resembles the “pruning” step aknowledged also by Hui et al., but, a further form related to second-layer links arises as typically occurs in observational studies. Finally, we perform a full Bayesian analysis instead of adopting the empirical Bayes approach followed by Hui et al.. Actually, our model-based tenet map, compared to the original version, features some more complexities, in addition to those inherent to the connection structure above outlined. We show that the probabilistic structure can be furtherly enriched by developing a three-stage model which accounts for dependence either of data or of parameters. The investigation of the empirical support and the degree of paradigm consensus of new economic theories of the firm motivated the development of the proposed methodology. In this paper, the Transaction Cost Economics view of the firm is tested by a tenet map analysis. The construction of a “consensus map”, which properly summarizes a set of individual maps, can help clarifying which and how many tenets (as well as the way they are practically operationalized) are more corroborated by empirical evidence. Moreover, the empirical evidence of one theory between separate groups—such as time periods or application areas—as well as the relative success of separate theories can be gauged by a comparison of the associated consensus maps generated according to different strengths of link probability.

Bayesian Concept Maps for assessing the empirical support and consensus for new economic theories of the firm

TREVISANI, MATILDE;BUSANA, CLARA
2008-01-01

Abstract

A concept map is a graph model comprised of concepts and undirected links which represent connections between different concepts. It has been widely used in psychology, education, and more recently introduced in marketing. Concept maps have been analysed heuristically or algorithmically until the recent proposal of Hui et al. (2008). They develop a probability model that provides a unified modelling framework for the analysis of concept maps. In this paper we extend this modelling framework in order to make it suitable for testing the empirical evidence of theories or main tenets of these. We identify a theory by a set of core propositions each essentially asserting that one set of independent variables affects one dependent variable. Moreover, every independent/dependent variable can have several operational definitions. Here, data consist of a selected sample of scientific articles from the empirical literature on the theory at issue; each article can include one or more tests of the theory being assessed. Differently from Hui et al., in our adapted version of concept map—that we call tenet map—the links of a map are two-layer: first-layer links connect the variables which have been related in the article at issue, second-layer links represent connections which have been found—consistently with the theory—statistically significant. In addition, either layer matrix of link-formation probabilities is block-symmetric for not all the independent variables can be connected to every dependent variable and each construct is associated with a set of operational definitions solely. Similarly to the original version, observed maps are censored: one form of censoring resembles the “pruning” step aknowledged also by Hui et al., but, a further form related to second-layer links arises as typically occurs in observational studies. Finally, we perform a full Bayesian analysis instead of adopting the empirical Bayes approach followed by Hui et al.. Actually, our model-based tenet map, compared to the original version, features some more complexities, in addition to those inherent to the connection structure above outlined. We show that the probabilistic structure can be furtherly enriched by developing a three-stage model which accounts for dependence either of data or of parameters. The investigation of the empirical support and the degree of paradigm consensus of new economic theories of the firm motivated the development of the proposed methodology. In this paper, the Transaction Cost Economics view of the firm is tested by a tenet map analysis. The construction of a “consensus map”, which properly summarizes a set of individual maps, can help clarifying which and how many tenets (as well as the way they are practically operationalized) are more corroborated by empirical evidence. Moreover, the empirical evidence of one theory between separate groups—such as time periods or application areas—as well as the relative success of separate theories can be gauged by a comparison of the associated consensus maps generated according to different strengths of link probability.
9784990444518
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11368/1857974
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact