The paper advances the log-generalized gamma distribution as a suitable generator of conditional skewness. Based on the NYSE composite daily returns an asMA-asQGARCH model along with skewness dynamics is estimated. The results indicate a skewness that varies between sizeable negative skewness and almost symmetry. The conditional variance and skewness measures are negatively correlated.
The integer-valued moving average model is advanced to model thenumber of transactions in intra-day data of stocks. The conditional mean andvariance properties are discussed and model extensions to includeexplanatory variables are offered. Least squares and generalized method ofmoment estimators are presented. In a small Monte Carlo study a feasibleleast squares estimator comes out as the best choice. Empirically we findsupport for the use of long-lag moving average models in a Swedish stockseries. There is evidence of asymmetric effects of news about prices on thenumber of transactions.
This article considers conditional duration models in which durations are in continuous time, but measured in grouped or discretized form. This feature of recorded durations in combination with a frequently traded stock is expected to negatively influence the performance of conventional estimators for intra-day duration models. A few estimators that account for the discreteness are discussed and compared in a Monte Carlo experiment. An EM-algorithm accounting for the discrete data performs better than those that do not. Empirical results are reported for trading durations in Ericsson B at Stockholmsbörsen for a 3-week period of July 2002. The incorporation of level variables for past trading is rejected in favour of change variables. This enables an interpretation in terms of news effects. No evidence of asymmetric responses to news about prices and spreads is found.
Event study methodology is used to analyse whether bad news in the form of Environmental (EV) incidents affect firm value negatively. An international sample of firms with EV incidents is studied. It is found that EV incidents are generally associated with the loss of value. For European firms, the loss is statistically significant and the magnitude of the abnormal returns should be of economic significance to corporations and investors. The results are not sensitive to multiple variations in methodology, including the use of international versions of the market model as well as of multi-factor models of the Fama-French type. Results are also robust to different parametric and nonparametric test statistics.