http://repub.eur.nl/res/concept/jel-C19/ Recent publications classified by JEL Code C19 en http://repub.eur.nl/static-eur/img/logo.png http://repub.eur.nl http://repub.eur.nl/res/pub/40377/ 2013-06-18T00:00:00Z The purpose of the paper is to discuss ten things potential users should know about the limits of the Dynamic Conditional Correlation (DCC) representation for estimating and forecasting time-varying conditional correlations. The reasons given for caution about the use of DCC include the following: DCC represents the dynamic conditional covariances of the standardized residuals, and hence does not yield dynamic conditional correlations; DCC is stated rather than derived; DCC has no moments; DCC does not have testable regularity conditions; DCC yields inconsistent two step estimators; DCC has no asymptotic properties; DCC is not a special case of GARCC, which has testable regularity conditions and standard asymptotic properties; DCC is not dynamic empirically as the effect of news is typically extremely small; DCC cannot be distinguished empirically from diagonal BEKK in small systems; and DCC may be a useful filter or a diagnostic check, but it is not a model. Caporin, M. McAleer, M.J. http://repub.eur.nl/res/pub/39433/ 2013-03-21T00:00:00Z The purpose of the paper is to discuss ten things potential users should know about the limits of the Dynamic Conditional Correlation (DCC) representation for estimating and forecasting time-varying conditional correlations. The reasons given for caution about the use of DCC include the following: DCC represents the dynamic conditional covariances of the standardized residuals, and hence does not yield dynamic conditional correlations; DCC is stated rather than derived; DCC has no moments; DCC does not have testable regularity conditions; DCC yields inconsistent two step estimators; DCC has no asymptotic properties; DCC is not a special case of GARCC, which has testable regularity conditions and standard asymptotic properties; DCC is not dynamic empirically as the effect of news is typically extremely small; DCC cannot be distinguished empirically from diagonal BEKK in small systems; and DCC may be a useful filter or a diagnostic check, but it is not a model. Caporin, M. McAleer, M.J. http://repub.eur.nl/res/pub/14048/ 2008-10-09T00:00:00Z We propose a first order bias correction term for the Gini index to reduce the bias due to grouping. The first order correction term is obtained from studying the estimator of the Gini index within a measurement error framework. In addition, it reveals an intuitive formula for the remaining second order bias which is useful in empirical analyses. We analyze the empirical performance of our first order correction term using income data for 15 European countries and the US, and show that it reduces a considerable share of the bias due to grouping. Ourti, T.G.M. van Clarke, Ph. http://repub.eur.nl/res/pub/18659/ 2008-08-01T00:00:00Z We provide in this article a number of new insights into the methodological discussion about author co-citation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors' co-citation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. We show by means of an example that the choice of an appropriate similarity measure has a high practical relevance. Finally, we discuss the use of similarity measures for statistical inference. Eck, N.J.P. van Waltman, L.R. http://repub.eur.nl/res/pub/10889/ 2007-12-13T00:00:00Z We provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance. Eck, N.J.P. van Waltman, L.R. http://repub.eur.nl/res/pub/6726/ 2005-06-28T00:00:00Z We propose a new test of the stochastic dominance efficiency of a given portfolio over a class of portfolios. We establish its null and alternative asymptotic properties, and define a method for consistently estimating critical values. We present some numerical evidence that our tests work well in moderate sized samples. Post, G.T. Linton, O. Whang, Y-J. http://repub.eur.nl/res/pub/923/ 2003-09-24T00:00:00Z In this study we propose the use of the Student's t dependence function to model dependence between asset returns when conducting stress tests. To properly include stress testing in a risk management system, it is important to have accurate information about the (joint) probabilities of extreme outcomes. Consequently, a model for the behavior of risk factors is necessary, specifying the marginal distributions and their dependence. Traditionally, dependence is described by a correlation matrix, implying the use of the dependence function inherent in the multivariate normal (Gaussian) distribution. Recent studies have cast serious doubt on the appropriateness of the Gaussian dependence function to model dependence between extreme negative returns. The student's t dependence function provides an attractive alternative. In this paper, we introduce four tests to analyze the empirical fit of both dependence functions. The empirical results indicate that probabilities assigned to stress tests are largely influenced by the choice of dependence function. The statistical tests reject the Gaussian dependence function, but do not reject the Student's t dependence function. Kole, H.J.W.G. Koedijk, C.G. Verbeek, M.J.C.M. http://repub.eur.nl/res/pub/431/ 2003-06-18T00:00:00Z Coefficient Alpha, which is widely used in empirical research, estimates the reliability of a test consisting of parallel items. In practice it is difficult to compare values of alpha across studies as it depends on the number of items used. In this paper we provide a simple solution, which amounts to computing the confidence intervals of an alpha, as these intervals automatically account for differences across the numbers of items. We also give appropriate statistics to test for significant differences of alpha values across studies. Koning, A.J. Franses, Ph.H.B.F. http://repub.eur.nl/res/pub/430/ 2003-06-13T00:00:00Z We analyze if the value-weighted stock market portfolio is second-order stochastic dominance (SSD) efficient relative to benchmark portfolios formed on market capitalization, book-to-market equity ratio and industry classification. During the period from the mid-1970s to the late 1980s, the market portfolio is significantly mean-variance inefficient. During this period, the market portfolio generally also is significantly SSD inefficient. This suggests that mean-variance inefficiency cannot be explained by omitted return moments like higher-order central moments or lower partial moments. Post, G.T. http://repub.eur.nl/res/pub/319/ 2003-04-29T00:00:00Z Empirically, co-skewness of asset returns seems to explain a substantial part of the cross-sectional variation of mean return not explained by beta. Thisfinding is typically interpreted in terms of a risk averse representativeinvestor with a cubic utility function. This comment questions thisinterpretation. We show that the empirical tests fail to impose risk aversionand the implied utility function takes an inverse S-shape. Unfortunately, thefirst-order conditions are not sufficient to guarantee that the market portfoliois the global maximum for an inverse S-shaped utility function, and ourresults suggest that the market portfolio is more likely to represent theglobal minimum than the global maximum. In addition, if we impose riskaversion, then co-skewness has minimal explanatory power. Post, G.T. Vliet, P. van http://repub.eur.nl/res/pub/279/ 2003-03-04T00:00:00Z This paper discusses statistical inference on the second-order stochastic dominance (SSD) efficiency of a given portfolio relative to all portfolios formed from a set of assets. We derive the asymptotic sampling distribution of the Post test statistic for SSD efficiency. Unfortunately, a test procedure based on this distribution involves low power in small samples. Bootstrapping is a more powerful approach to sampling error. We use the bootstrap to test if the Fama and French value-weighted market portfolio is SSD efficient relative to benchmark portfolios formed on market capitalization and book-tomarket equity ratio. During the late 1970s and during the 1980s, the market portfolio is significantly SSD inefficient, even if we use samples of only 60 monthly observations. This suggests that the size and book-to-market effects cannot be explained by omitted risk factors like higher-order central moments or lower partial moments. Post, G.T. http://repub.eur.nl/res/pub/163/ 2002-02-05T00:00:00Z We develop a Stochastic Dominance methodology to analyze if new assets expand the investment possibilities for rational nonsatiable and risk-averse investors. This methodology avoids the simplifying assumptions underlying the traditional mean-variance approach to spanning. The methodology is applied to analyze the stock market behavior of small firms in the month of January. Our findings suggest that the previously observed January effect is remarkably robust with respect to simplifying assumptions regarding the return distribution. Post, G.T. http://repub.eur.nl/res/pub/164/ 2002-02-05T00:00:00Z We derive an empirical test for third-order stochastic dominance that allows for diversification between choice alternatives. The test can be computed using straightforward linear programming. Bootstrapping techniques and asymptotic distribution theory can approximate the sampling properties of the test results and allow for statistical inference. Our approach is illustrated using real-life US stock market data. Post, G.T. http://repub.eur.nl/res/pub/129/ 2001-11-06T00:00:00Z We propose linear programming tests for spanning and intersection based on stochastic dominance rather than mean-variance analysis. An empirical application investigates the diversification benefits to US investors from emerging equity markets. Post, G.T. http://repub.eur.nl/res/pub/102/ 2001-07-03T00:00:00Z Recently, a Competitive Exception Learning Algorithm (CELA) was introduced [1, 2]. This algorithm establishes an optimal mapping from a (continuous) M-dimensional input sample space to an N-dimensional (continuous) output sample space. CELA is aimed to discover regimes (i.e. local behavior in the input sample space) for which the conditional probability distribution in the output sample space systematically deviates from the average unconditional distribution. Previous papers on CELA dealt with the introduction of the algorithm by sketching its background and by describing the algorithmic sub-steps. The algorithm was tested successfully on both simulated and real world data, mainly in the field of financial markets. However, until now a precise and firm theoretical foundation of CELA is still lacking. The current paper resolves this imperfection. The contribution to be made here is twofold. First, we present, in section 2, a probability theory and statistics of fuzzy sets which in itself is interesting. Second, we re-formulate, in section 3, the CELA-algorithm within the probabilistic fuzzy framework introduced. We finalize with a discussion and outlook. Berg, J. van den Bergh, W.M. van den Kaymak, U. http://repub.eur.nl/res/pub/131/ 2001-01-01T00:00:00Z Marketing problems sometimes concern the analysis of dichotomous variables, like for example ``buy'' and ``not buy'' and ``respond'' and ``not respond''. It can happen that one outcome strongly outnumbers the other, for example when many households do not respond (to a direct mailing, for example). Standard econometric methods would imply the collection of many data to obtain precise estimates and this can be rather costly. To cut back costs, we propose to implement a non-random sampling scheme and to correct for the subsequent sample selection bias in the econometric model. In this paper we put forward the relevant method, which does not lead to a loss in precision. Our illustration suggests an opportunity to collect 60\\% less data points. Donkers, A.C.D. Franses, Ph.H.B.F. Verhoef, P.C. http://repub.eur.nl/res/pub/132/ 2001-01-01T00:00:00Z One of the aims of direct marketing in practice is to target the most profitable customers in the database at hand. This selection is often done based on observed behavior in the past. As a consequence, databases arising from the responses to direct mailings are not a random sample from all potential respondents. When not all heterogeneity is observed, part of the target selection rule will be based on the unobserved heterogeneity, so selection is endogenous. Treating an endogenously selected sample as a random sample results in inconsistent parameter estimates, which in general also harms the predictive performance of the model. We develop an adjustment to the likelihood of the model that corrects for the endogenous sample selection. We apply this technique to the selection of mail targets for a charitable organization. In the application we also show that, based on a model for the response rate and the amount donated simultaneously, we can create a target selection rule that maximizes expected revenues. Such a selection rule outperforms selection rules based on response rates or donated amount only. The traditional approach of maximizing response is therefore not the optimal approach to target selection. Donkers, A.C.D. Jonker, J-J. Franses, Ph.H.B.F. Paap, R.