Overload List
| # | Signature | Description |
|---|---|---|
| 1 | procedure TriangularCDFInv(const P: TDenseMtxVec; a: Double; b: Double; c: Double; const Res: TDenseMtxVec); | Triangular distribution PPF (vectorized). |
| 2 | function TriangularCDFInv(p: Double; a: Double; b: Double; c: Double): Double; | Triangular distribution point percent function (PPF). |
Overload 1: procedure TriangularCDFInv(const P: TDenseMtxVec; a: Double; b: Double; c: Double; const Res: TDenseMtxVec);
Triangular distribution PPF (vectorized).
| # | Name | Description |
|---|---|---|
| 1 | P | Defines distribution probabilities, real vector or matrix with values within closed interval [0,1]. |
| 2 | a | Distribution locagtion parameter, real value, smaller than parameter b. |
| 3 | b | Distribution scale parameter, real value, greater than parameter a. |
| 4 | c | Distribution shape parameter, real value on closed interval [a,b]. |
| 5 | Res | After calculation stores the PPF calculated from P, a,b and c. Length and Complex properties of Res are adjusted automatically to match Length and Complex properties of P. |
Result: stored in self (calling object)
Overload 2: function TriangularCDFInv(p: Double; a: Double; b: Double; c: Double): Double;
Triangular distribution point percent function (PPF).
| # | Name | Description |
|---|---|---|
| 1 | p | Probability, real value on closed interval [0,1]. |
| 2 | a | Lower bound, real value, smaller than b. |
| 3 | b | Upper bound, real value, greater than a. |
| 4 | c | Mode (peak), real value on closed interval [a,b]. |
Returns: Double - the Triangular distribution point percent function (PPF) for probability p using parameters a, b and c. Requires b > a, a <= c <= b and p in [0,1], otherwise the result is NAN.
Remarks:
With the transition probability t = (c - a)/(b - a), the inverse triangular cumulative distribution function (quantile) is
CDF^(-1)(p| a,b,c)={ a+sqrt(p (b-a)(c-a)), if amp; 0 <= p <= t
{ [6pt] b-sqrt((1-p) (b-a)(b-c)), if amp; t
It is the solution x of TriangularCDF(x | a,b,c) = p. Domain: probability p in [0,1], b > a, a <= c <= b. For p outside [0,1] or invalid parameter ordering the result is NAN.