An Adaptive Moving Average Smoother Using Standard Deviation

Summary

This document describes a price smoother whose calculation period can be fractional and whose adaptation is based on standard deviations. It distinguishes the method from a true Jurik moving average, while noting that it resembles versions often labeled as Jurik smoothers. The adaptation can be disabled by setting its adaptation period to 1.

The author presents it as a filtering tool and claims its value inheritance avoids the repainting issue associated with many circulating JMA implementations. The tradeoff is potentially lower responsiveness than a genuine JMA. Longer adaptation periods are said to work better, with an example configuration using an adaptation period of 50 and a calculation period of 25, but no chart, performance statistics, or systematic comparison is included. The settings are therefore suggestions to experiment with, not evidence that the smoother improves trading results.

Key ideas

• The smoother adapts its calculation using a standard deviation method.
• Its adaptation can be turned off by setting the adaptation period to 1.
• The author says value inheritance is intended to prevent repainting seen in many JMA variants.
• The smoother may respond more slowly than a true Jurik moving average, and the document gives no comparative test results.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.