Econometrie

Oil price volatility and stock markets

Thu, 01 Jan 2009 00:00:01 GMT

Dalakouras, Dimitri

Primary aim of this research is to contribute to the literature on oil prices and stock markets by studying the relation between oil price volatility and stock market volatility. We use a large sample of developed and emerging stock market indices, based on monthly observations over the period January 1982 – December 2008. Volatility is approximated as realized volatility and our methodology is based on regression analysis. Results indicate that one month lagged oil price volatility has significant predicting power in a considerable number of stock market indices, despite the high persistence of stock market volatility. The explanatory power of our model is maximized with the inclusion of an additional lag of five or ten days, which is consistent with the existence of delayed reaction by investors. Furthermore, sector analysis reveals that oil price volatility has greater influence in non oil related industries than in oil related. Additionally, we find strong evidence of asymmetric effects of oil prices on stock market returns. The results denote that increases on oil price appear to have a larger (and negative) impact on the stock market indices than the decreases. Moreover, the existence of asymmetric effects on oil price volatility to stock market volatility is not supported by empirical evidence.

Effects of the Length of the Planning Horizon in a Master Surgical Schedule

Tue, 17 Mar 2009 00:00:01 GMT

Evers, L.

Currency Hedging for Long Term Investors with Liabilities

Wed, 29 Apr 2009 00:00:01 GMT

Nes, G.P. van

This thesis considers a long term investor with liabilities that invests internationally and therefore runs currency risk and has to decide on how much of this risk it wants to hedge. The purpose of this thesis is to optimize this currency hedging decision. To achieve this, a mean-variance framework is derived that includes exchange rates and liabilities. It will be found that the investment horizon of the investor will play an important role in the optimal currency decision and that this decision also depends on the characteristics of the investor. Furthermore, it will be found that the total exposure to foreign currency in the portfolio is not important in determining the optimal currency decision but that this decision is mainly determined by the correlations of the exchange rates with the assets and the liabilities.

Political premiums and election cycles in the UK stock market, 1965 - 2008

Fri, 01 May 2009 00:00:01 GMT

Ackermans, M.

ABSTRACT This thesis analyses British stock market returns between 1965 and 2008, by testing two theories that describe the interaction between economics and politics: the political policy theory and the political business cycle theory. Despite that (both nominal and excess) stock market returns were higher in times of Conservative Party dominance, a political premium was found for times of a Labour government: corrected for economic variables that help to explain excess returns, the stock market performs better under a Labour administration and this outperformance is statistically significant. Furthermore, in UK stock market returns no election cycle was found. Since inflation rates do show a cyclical pattern that follows election dates, the political business cycle theory is not rejected: these outcomes just show that the stock market is too efficient to be ‘fooled’ by a government aiming for re-election in its economic policy.

The Effect of Higher Agricultural Commodity Prices on Producers in Sub Saharan Africa

Thu, 07 May 2009 00:00:01 GMT

Heuvelen, G. H. van

Using the Midas approach for now- and forecasting Colombian GDP

Mon, 11 May 2009 00:00:01 GMT

Castaneda, Cabriel

This study applies the Factor-MIDAS approach (Marcellino and Schumacher, 2007) in the forecasting of Colombian GDP. The main objective is to test the performance of the predictions generated under this framework by means of Mean Squared Error values and forecast evaluation tests. Two forms of MIDAS (Mixed Data Sampling) projections were studied, MIDAS with exponential almon and MIDAS with unrestricted coefficients. Also, two methods for factor were used, one based on the EM algorithm and the other based on the state-space model with the Kalman filter. Both methods are able to handle missing values at the end of the sample due lags of publication. In addition, the factors were calculated using a large dataset of macroeconomic variables and a subset of it. The regressions were estimated using fixed factor lags along with an automatic lag selection. The nowcast and forecast performance of these regressions were compared with a simple benchmark model AR(1) model. The empirical findings show in general, that the MIDAS projections do not outperform the benchmark when the forecast tests are applied. There is only slight evidence that the MIDAS projections do better in the nowcast horizon. In terms of lower Mean Squared Error values, the better results are achieved when the number of factor lags is at most 3. Moreover, in this case there is no difference in the performance of these two projections. The automatic factor lag selection did not show any improvement compared to the use of very few fixed factor lags.

Clusering in SaaS networks

Thu, 25 Jun 2009 00:00:01 GMT

Gaast, J. van der

Rietveld, N.

Creditcardgebruik en invloed tarifering bij internetaankopen

Tue, 30 Jun 2009 00:00:01 GMT

Everdingen, Y. van

A comparison of several heuristics for crew rescheduling at NS

Fri, 10 Jul 2009 00:00:01 GMT

Velden, R. van der

Stock Splits en Stock Dividenden

Thu, 16 Jul 2009 00:00:01 GMT

Groot Baltink, R.F.J.

Chasing Bulls and Fleeing Bears Cross-Countries

Fri, 17 Jul 2009 00:00:01 GMT

Opdurp, J.J. van

In dit artikel beschrijven we twee manieren om bull- en bearmarkten te voor- spellen. We doen dit enerzijds door met een multinomiaal logit model voor elke maand opnieuw een voorspelling te doen voor de Amerikaanse S&P 500 Index en de Britse FTSE All Share Index vanaf 1981. Anderzijds gebruiken we binomiale logit modellen om voorspellingen te doen voor elke index apart. Het doel van dit on- derzoek is het onderzoeken of een multinomiaal logit model met twee indexen beter presteert dan twee aparte binomiale logit modellen voor elke index. Als afhankelij- ke variabele defini ̈eren we voor elke index een bull- of bearmarkt wanneer de index gestegen/gedaald is met een bepaald drempelpercentage ten opzichte van een locaal minimum of maximum, respectievelijk. We gebruiken als onafhankelijke variabelen zowel macro-economische als financi ̈ele data. Bij het multinomiale model slagen we erin om, afhankelijk van het selectiecriterium dat we hanteren, tot bijna 67% van de maanden juist te voorspellen. Een samenvoeging van twee losse binomiale logit modellen haalt hierbij een out-of-sample hitrate van 65%. Hierna gebruiken we onze voorspellingen om verschillende handelsmodellen op te zetten. Afhankelijk van onze voorspellingen beslissen we iedere maand opnieuw of we investeren in de Amerikaanse index, de Britse index, een korte termijn deposito of een combinatie hiervan. Hiermee haalt het multinomiale logit model maximaal een gemiddelde jaarrendement over 28 jaar en 2 maanden van ruim 7.35%, in tegenstelling tot de binomiale logit modellen, waarmee 6.73% behaald wordt.

Butterfly strategie met het arbitrage-vrije Nelson-Siegel model

Mon, 20 Jul 2009 00:00:01 GMT

Meijers, T. (Tanny)

Het arbitrage vrije Nelson-Siegel (AFNS) model beschrijft de fluctuaties en voorspelt de rente-termijnstructuur aan de hand van de level, slope en curvature factor. De voorspellingen worden gebruikt om de stijging of de daling van de slope of curvature factor van het AFNS model te bekijken. Aan de hand van een handelsregel wordt er een butterfly swap gevormd voor de gegeven voorspelling. Hieruit blijkt dat er met het AFNS model butterfly swaps gevormd kunnen worden, die een goede return leveren en een laag risico hebben in verhouding met de return.

Determining the optimal recovery policy in liner shipping networks using a Markov decision model

Tue, 21 Jul 2009 00:00:01 GMT

Mulder, J.

Adjusting the rolling stock allocation in case of disruptions

Tue, 21 Jul 2009 00:00:01 GMT

Louwerse, I.

A questionnaire-based efficacy index to measure the impact on wellbeing of development interventions in sub-Saharan Africa

Thu, 23 Jul 2009 00:00:01 GMT

Kandelaars, E.

A model for regime switching behavior in the joint distribution of stock and bond returns

Thu, 23 Jul 2009 00:00:01 GMT

Engelen, C.

The paper demonstrates the application of a Markov Switching Copula model on stock-bond relationships. This method is sufficiently flexible as it allows dependency to be modeled separately in two regimes, representing alternate bear and bull market climates. Each regime is described by a copula with asymmetric marginal density functions, allowing the so described Flight to Quality, a curious negative dependence in a bear market climate, to be described separately from the overall positive dependence in bull market climate. The optimization procedure combines Markov switching and copula theory to produce a well fitted description of the dependence structure between national stock and government bond indices. The model successfully identifies flight to quality movement and permanent shifts in market behavior.

Het voorspellen van het teken van style spreads voor de Amerikaanse markt

Fri, 31 Jul 2009 00:00:01 GMT

Ovaa, T.M. (Thomas)

Bull en Bear markten in verschillende investeringklasen

Fri, 31 Jul 2009 00:00:01 GMT

Hogerwerf, J.

Dit onderzoek is een uitbreiding van Hogerwerf et al (2009). Ik onderzoek of het mo-gelijk is aan de hand van een binair model te voorspellen wanneer investeringsklas-sen (aandelen, obligaties, grondstoffen en onroerend goed) bullish of bearish zullen zijn. Resultaat is dat het ongeveer 70 procent van de tijd mogelijk is de staat van een markt te bepalen. Een extra bivariate probit model wordt toegevoegd, waain het mo-gelijk is de verschillende investeringsklassen te combineren, maar het blijkt dat toe-voeging van dit model geen verbetering betekent.

Het Markov switching model met variabele overgangskansen toegepast op de S&P 500

Fri, 31 Jul 2009 00:00:01 GMT

Rooijen, V.M. van

Het hedgen van valutarisico

Fri, 31 Jul 2009 00:00:01 GMT

Mooren, H.P.H.B.

In dit onderzoek wordt de correlatie tussen een aandelenkoers en een wisselkoers voorspeld met drie modellen: DCC, Scalar BEKK en MA63. Met behulp van deze correlatieschattingen wordt een optimale hedgeratio bepaald en aan de hand van de bijbehorende utility wordt het best presterende model gekozen.