« AUTOCHARTIST - Detect chart pattern automatically! | Main | List of keyboard shortcuts for Metatrader Platform »
Time Series Forecast (TSF) indicator
By Paulus | August 21, 2007
The Time Series Forecast (TSF) indicator is based on linear regression calculations using the Least Squares method. Linear regression is a statistical tool used to predict future forex market values relative to past values. TSF attempts to ‘predict’ the future value of a forex market by determining the upward or downward bias of a trend and extending that calculation into the future.For example, if prices are trending up, TSF attempts to logically determine the upward bias of the price relative to the current price and extend that calculation forward. When the forex market price is above the indicator, the trend is considered up. When the forex market price is below the indicator, the trend is considered down.
Additionally, many analysts believe when prices rise above or fall below the indicator line; prices will likely pull back to the line. The TSF indicator also monitors the current trend to determine if a change in direction occurred.
The Time Series Forecast indicator is similar to the Linear Regression indicator with the exception of two significant differences. The first difference is that TSF plots its line forward (to the right of the chart) by the number of bars specified by the BarsPlus input. The second difference is the default Length input value used for the TSF is much shorter because the plot line is extended forward.
A larger Length input would create a grossly exaggerated plot and would not be as reliable as a shorter-term length when analyzing trends and price activity.
Thus, the Time Series Forecast function displays the statistical trend of a security’s price over a specified time period based on linear regression analysis. Instead of a straight linear regression trendline, the Time Series Forecast plots the last point of multiple linear regression trendlines. This is why this indicator may sometimes referred to as the “moving linear regression” indicator or the “regression oscillator.”
Because a linear regression line is a straight line as close as possible to all of the given values, a Time Series Forecast does not exhibit as much delay as a Moving Average when adjusting to price changes. This is because the indicator is continuously “fitting” itself to the data rather than simply averaging them. Note that this type of prediction is purely mathematical as it is ultimately the equivalent of drawing a line through the recent points and projecting that line forward.
The Time Series Forecast at the beginning of a data series will not be defined until there are enough values to fill the given period.
Topics: Forex Indicators |
Comments
You must be logged in to post a comment.