Moderated regression is a commonly used technique within the behavioral sciences. The power of such analyses, however, is dependent on the strength of the moderator relationship and the distribution of the moderator variable. This study compares the traditional moderated technique with a technique designed to increase the probability of the indication of a moderator variable. The results indicate that, often, the detection of moderator variables is not so much dependent on their existence but, rather, is dependent on their strength. The results also indicate that the ability to detect moderators also depends on the distribution of the moderator variable. Finally, the results indicate that a higher probability of detecting a moderator exists if the interaction is entered into the regression first.
The number of student-managed investmentfinds has grown rapidly in recent years. In the four decades since the first student-managed investment fimd was established at Gannon University, the number of such&nds has grown at a rate of less than one per year to thirty-four in 1993. However, that rate of growth has changed dramatically in recent years. Oak Associates Ltd., the Akron, Ohio based investment-management com- pany, has funded ten student-managed investment finds since January 1996. The fund established by Oak Associates Ltd. at The University of Akron provides students with the opportunity to learn about investing real money on a real-time basis. The Oak Grant provides significant educational opportunities at the University and some real chal- lenges in the organization and management of the finds.
This paper examines the forecasting accuracy and the cost effectiveness of time series models with time-varying coefficients. A simulation study investigates the potential forecasting benefits of a proposed Kalman filter type adaptive estimation and forecasting approach. It is found that: (1) When appropriate, the time-varying coefficient approach leads to better forecasts than the constant coefficient procedures. (2) A simple decision rule, which indicates whether time-varying coefficient models are in fact needed, increases the computational efficiency.statistics, forecasting, time series
In this paper we use time‐series models to investigate the presence of autoregression, random variation, and random walk movements of historic equity risk premiums. An autoregressive risk premium is found for 1926–58, but random variation around a much lower risk premium mean is found for 1959–90. This finding is not sensitive to holding‐period length, the choice of the risk‐free rate proxy, or January/July seasonal effects.
In this paper a time-varying coefficient model is developed using a Kalman filter methodology to test the term structure of interest rates. Since the model is characterized by continuing revision of the estimates when new information arrives, it is capable of capturing the dynamic interest rate behavior, thereby increasing the forecasting accuracy of the future spot rates. With the constant expectations hypothesis rejected, the forecasting accuracy is substantially increased.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.