Testing cumulative prediction errors in event study methodology

Article Abstract:

Event study methodology is a technique that is often used in financial analysis. It involves accounting research based on market data and relies on regression analysis to describe the interactions between securities prices and economic events. One important issue involved in such analyses is the method of testing for abnormal returns. Analysis of cumulative prediction errors and serial correlation, heteroskedasticity and non-normality in residuals reveals that the conventional Patell residual test fails to obtain the correct standard error.

Methods, Usage, Error analysis (Mathematics)

---

Randomized unit root processes in modelling and forecasting financial time series: theory and applications

Article Abstract:

Several techniques for testing random unit roots and modeling stochastic unit root processes were developed based on the theory that the levels of a financial time series have a stochastic character. The techniques were then employed to forecast bond yields and stock price indices using several time series from Apr. 1, 1986 to Dec. 29, 1989, and from Jan. 1, 1984 to Jan. 1, 1986, respectively. The results confirmed the random unit root pattern of the data sets.

Research, Stock price indexes, Bonds, Bonds (Securities), Stochastic processes, Time-series analysis, Time series analysis

---

Non-linear forecasting of financial time series: an overview and some new models

Article Abstract:

Several studies on parametric methods of modeling and forecasting financial time series are presented. These nonlinear approaches improve on traditional linear models of trading schemes. In addition, several new models are illustrated using 60-year time series obtained from the London Stock Exchange's Financial Times-Institute of Actuaries 30 index.

Models, Nonlinear theories

Similar abstracts:

• Abstracts: Testing cross-section correlation in panel data using spacings. Determining the number of primitive shocks in factor models
• Abstracts: Forecasting time series with outliers. Optimal prediction with nonstationary ARFIMA model. A semi-parametric time-series approach in modeling hourly electricity loads
• Abstracts: Federal budget projections: a nonparametric assessment of bias and efficiency. Exact nonparametric orthogonality and random walk tests
• Abstracts: Maximum-likelihood estimation of fractional cointegration with an application to U.S. and Canadian bond rates

This website is not affiliated with document authors or copyright owners. This page is provided for informational purposes only. Unintentional errors are possible.