Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: https://hdl.handle.net/10419/86378 
Erscheinungsjahr: 
2006
Schriftenreihe/Nr.: 
Tinbergen Institute Discussion Paper No. 06-060/3
Verlag: 
Tinbergen Institute, Amsterdam and Rotterdam
Zusammenfassung: 
In this paper we perform a meta-analysis on empirical estimates of the impact between investment and uncertainty. Since the outcomes of primary studies are largely incomparable with respect to the magnitude of the effect, our analysis focuses on the direction and statistical significance of the relationship. The standard approach in this situation is to estimate an ordered probit model on a categorical estimate, defined in terms of the direction of the effect. The estimates are transformed into marginal effects, in order to represent the changes in the probability of finding a negative significant, insignificant, and positive significant estimate. Although a meta-analysis generally does not allow for inferences on the correctness of model specifications in primary studies, our results give clear directions for model building in empirical investment research. For example, not including factor prices in investment models may seriously affect the model outco! mes. Furthermore, we find that Q-models produce more negative significant estimates than other models do, ceteris paribus. The outcome of a study is also affected by the type of data used in a primary study. Although it is clear that meta-analysis cannot always give decisive insights into the explanations for the variation in empirical outcomes, our meta-analysis shows that we can explain to a large extent why empirical estimates of the investment-uncertainty relationship differ.
Schlagwörter: 
investment
uncertainty
meta-analysis
JEL: 
C10
D21
D80
E22
Dokumentart: 
Working Paper
Erscheint in der Sammlung:

Datei(en):
Datei
Größe
316.09 kB





Publikationen in EconStor sind urheberrechtlich geschützt.