http://repub.eur.nl/res/concept/jel-C40/ Recent publications classified by JEL Code C40 en http://repub.eur.nl/static-eur/img/logo.png http://repub.eur.nl http://repub.eur.nl/res/pub/8212/ 2006-12-21T00:00:00Z Wherever we are, networks are all around us. The roads that we travel form a network. The websites that we visit form an enormous information network. But, above all, we are part of a network ourselves, the network of social contacts and relations. These networks play an important role in economic life, but it is not always clear in what way. This thesis analyzes problems related to three types of networks: a network of collaborating economists, a network of job contacts, and a transport network. The thesis uses a combination of theoretical models and novel empirical techniques to show how network effects shape markets and societies. Leij, M.J. van der http://repub.eur.nl/res/pub/90/ 2001-05-18T00:00:00Z We consider the issues of noise-to-signal estimation, finite sample performance and hypothesis testing for the nonparametric efficiency estimation technique proposed in Cherchye, L., T. Kuosmanen and G. T. Post (2001) 'Nonparametric efficiency estimation in stochastic environments', forthcoming in Operations Research. In addition, we apply the technique for analyzing European banks. Cherchye, L. Post, G.T. http://repub.eur.nl/res/pub/72/ 2001-02-12T00:00:00Z This paper develops a novel statistic for firm efficiency called efficiency depth that allows for statistical inference in case of errors-in-variables. We derive statistical tests that require minimal statistical assumptions; neither the sample distribution nor the noise level is required. An empirical illustration for European banks illustrates that - despite the minimal assumptions- the tests can have substantial discriminating power in practical applications. Kuosmanen, T. Post, G.T. http://repub.eur.nl/res/pub/21/ 2000-05-18T00:00:00Z In this paper we present a new methodology to infer the implied risk-neutral distribution function from European-style options. We introduce a skewed version of the Student-t distribution, whose main advantage is that its shape depends on only four parameters, of which two directly control for the levels of skewness and kurtosis. We can thus easily vary parameters to compare different distributions and use the parameters as inputs to price other options. We explain the method, provide some empirical results and compare them with the results of alternative models. The results indicate that our model provides a better fit to market prices of options than the Shimko or implied tree models, and has a lower computation time than most other models. We conclude that the skewed Student-t method provides a good alternative for European-style options. Jong, C.M. de Huisman, R.