Moving Averages for Market Timing

Abstract

This paper begins by presenting the moving average methodology of detecting the direction of a trend and identifying turning points in the trend in real time. The paper then proceeds to introduce the general weighted moving average, derives some of its key properties, and discusses how to quantitatively assess the two important characteristics of a moving average: the average lag time and the smoothness. Finally the paper aims to give an overview of some specific types of moving averages used in market timing. These types include regular moving averages, moving averages of moving averages, and mixed moving averages with less lag time. Different types of moving averages are compared to each other with respect to their smoothness and lag time.The paper argues that the notion of the “lag time” of a moving average is an elusive concept. The analysis provided in this paper suggests that there are two issues with the quantity known as the “average lag time” of a moving average. First, the average lag time has little to do with the delay in the identification of turning points in a trend. Second, the average lag time can be easily manipulated. For example, the average lag time can be reduced to zero by worsening the tradeoff between the smoothness of a moving average and its delay in turning point identification.