Category: Advanced Indicator Set 1
Input parameters
Name
|
Setting
|
Default
|
Input series
|
Input Time Series
|
Close
|
Polynomial degree
|
0<= Integer <=100
|
2
|
Number of points
|
Integer >=1
|
20
|
Predict period
|
Integer >=0
|
1
|
Calculations
For the current bar the Polynomial Predict indicator calculates a polynomial p(t) through the most recent Number of points in the form:
p(t) = a0 + a1 * x(t) + a2 * x(t)^2 + … + aN * x(t) ^ N,
where a0..aN - polynomial coefficients, x(t) - X-coordinate value, and N - Polynomial Degree.
The goal of the polynomial regression is to find a set of coefficients a0, a1, …, aN, which minimize the error function Sum(y(t)-p(t))^2.
After polynomial coefficients are found, the indicator calculates a projected value for the Predict period into the future. The predicted value is drawn as a signal on the current bar.
For example, given default settings, the Polynomial Predict indicator takes the most recent 20 bars (including the current bar), draws a polynomial of second degree, computes a projected polynomial value for the next bar, and shows that projected value on the current bar.
|