http://repub.eur.nl/res/concept/jel-C89/ Recent publications classified by JEL Code C89 en http://repub.eur.nl/static-eur/img/logo.png http://repub.eur.nl http://repub.eur.nl/res/pub/19551/ 2010-03-01T00:00:00Z A term map is a map that visualizes the structure of a scientific field by showing the relations between important terms in the field. The terms shown in a term map are usually selected manually with the help of domain experts. Manual term selection has the disadvantages of being subjective and labor-intensive. To overcome these disadvantages, we propose a methodology for automatic term identification and we use this methodology to select the terms to be included in a term map. To evaluate the proposed methodology, we use it to construct a term map of the field of operations research. The quality of the map is assessed by a number of operations research experts. It turns out that in general the proposed methodology performs quite well. Eck, N.J.P. van Waltman, L.R. Noyons, E.C.M. Buter, R.K. http://repub.eur.nl/res/pub/19599/ 2010-02-01T00:00:00Z Respondents can vary strongly in the way they use rating scales. Specifically, respondents can exhibit a variety of response styles, which threatens the validity of the responses. The purpose of this article is to investigate how response style and content of the items affect rating scale responses. The authors develop a novel model that accounts for different types of response styles, content of items, and background characteristics of respondents. By imposing a bilinear parameter structure on a multinomial logit model, the authors graphically distinguish the effects on the response behavior of the characteristics of a respondent and the content of an item. The authors combine this approach with finite mixture modeling, yielding two segmentations of the respondents: one for response style and one for item content. They apply this latent-class bilinear multinomial logit model to the well-known List of Values in a cross-national context. The results show large differences in the opinions and the response styles of respondents and reveal previously unknown response styles. Some response styles appear to be valid communication styles, whereas other response styles often concur with inconsistent opinions of the items and seem to be response bias. Rosmalen, J.M. van Herk, H. van Groenen, P.J.F. http://repub.eur.nl/res/pub/14056/ 2008-12-03T00:00:00Z A term map is a map that visualizes the structure of a scientific field by showing the relations between important terms in the field. The terms shown in a term map are usually selected manually with the help of domain experts. Manual term selection has the disadvantages of being subjective and labor-intensive. To overcome these disadvantages, we propose a methodology for automatic term identification and we use this methodology to select the terms to be included in a term map. To evaluate the proposed methodology, we use it to construct a term map of the field of operations research. The quality of the map is assessed by a number of operations research experts. It turns out that in general the proposed methodology performs quite well. Eck, N.J.P. van Waltman, L.R. Noyons, E.C.M. Buter, R.K. http://repub.eur.nl/res/pub/10463/ 2007-07-10T00:00:00Z Respondents can vary significantly in the way they use rating scales. Specifically, respondents can exhibit varying degrees of response style, which threatens the validity of the responses. The purpose of this article is to investigate to what extent rating scale responses show response style and substantive content of the item. The authors develop a novel model that accounts for possibly unknown kinds of response styles, content of the items, and background characteristics of respondents. By imposing a bilinear structure on the parameters of a multinomial logit model, the authors can visually distinguish the effects on the response behavior of both the characteristics of a respondent and the content of the item. This approach is combined with finite mixture modeling, so that two separate segmentations of the respondents are obtained: one for response style and one for item content. This latent-class bilinear multinomial logit (LC-BML) model is applied to a cross-national data set. The results show that item content is highly influential in explaining response behavior and reveal the presence of several response styles, including the prominent response styles acquiescence and extreme response style. Rosmalen, J.M. van Herk, H. van Groenen, P.J.F. http://repub.eur.nl/res/pub/9401/ 2007-03-28T00:00:00Z In a recent paper in the Journal of the American Society for Information Science and Technology, Leydesdorff and Vaughan assert that raw cocitation data should be analyzed directly, without first applying a normalization like the Pearson correlation. In this report, it is argued that there is nothing wrong with the widely adopted practice of normalizing cocitation data. One of the arguments put forward by Leydesdorff and Vaughan turns out to depend crucially on incorrect multidimensional scaling maps that are due to an error in the PROXSCAL program in SPSS. Waltman, L.R. Eck, N.J.P. van http://repub.eur.nl/res/pub/927/ 2003-09-25T00:00:00Z In this paper we explore the theoretical and empirical problems of estimating average (excess) return and risk of US equities over various holding periods and sample periods. Our findings are relevant for performance evaluation, for estimating the historical equity risk premium, and for investment simulation. Using a unique set of US equity data series, comprising monthly prices and dividends based on consistent definitions over the 132 year period 1871-2002, we investigate the complex effect of temporal return aggregation and sample estimation error. Our major finding is that holding period risk and return statistics show an extraordinary sensitivity to the choice of the starting point in calendar time. For example, over the period 1926-2002 there is a difference of almost 140 basis points between the average annual total return starting in January compared to starting in July, and a difference of almost 7 (!) percentage points in estimated annual volatility. This is yet another way in which stock price seasonality manifests itself, but this ambiguity in the underlying estimation process seems completely neglected in the current literature. Hallerbach, W.G.P.M. http://repub.eur.nl/res/pub/928/ 2003-09-25T00:00:00Z In this paper we explore the relevance of dividends in the total equity return over longer time horizons. In addition, we investigate the effects of different reinvestment assumptions of dividends. We use a unique set of revised and corrected US equity data series, comprising monthly prices and dividends based on consistent definitions over the period 1871-2002 (132 years). Our findings are relevant for performance evaluation, for estimating the historical equity risk premium, and for investment simulation. Hallerbach, W.G.P.M. http://repub.eur.nl/res/pub/117/ 2001-10-18T00:00:00Z This paper proposes a new algorithm for target selection. This algorithm collects all frequent patterns (equivalent to frequent item sets) in a training set. These patterns are stored e?ciently using a compact data structure called a trie. For each pattern the relative frequency of the target class is determined. Target selection is achieved by matching the candidate records with the patterns in the trie. A score for each record results from this matching process, based upon the frequency values in the trie. The records with the best score values are selected. We have applied the new algorithm to a large data set containing the results of a number of mailing campaigns by a Dutch charity organization. Our algorithm turns out to be competitive with logistic regression and superior to CHAID. Pijls, W.H.L.M. Potharst, R. Kaymak, U. http://repub.eur.nl/res/pub/61/ 2000-12-05T00:00:00Z Due to the present-day memory sizes, a memory-resident database has become a practical option. Consequently, new methods designed to mining in such databases are desirable. In the case of disk-resident databases, breadth-first search methods are commonly used. We propose a new algorithm, based upon depth-first search in a set-enumeration tree. For memory-resident databases, this method turns out to be superior to breadth-first search. Pijls, W.H.L.M. Bioch, J.C.