Quantile-parameterized distribution

Uses your system voice; voice and rate in settings.

Snapshot

≈ 8 min read

Names in other languages

No names in other languages are held for this entry yet.

Article bodies are English and are not machine-translated. A name in another language is not a translation of the article.

A quantile-parameterized distribution (QPD) is a probability distribution that is directly parameterized by data. They were created to meet the need for easy-to-use continuous probability distributions flexible enough to represent a wide range of uncertainties, such as those commonly encountered in business, economics, engineering, and science. Because QPDs are directly parameterized by data, they have the practical advantage of avoiding the intermediate step of parameter estimation, a time-consuming process that typically requires non-linear iterative methods to estimate probability-distribution parameters from data. Some QPDs have virtually unlimited shape flexibility and closed-form moments as well.

Evidence and sources

A quantile-parameterized distribution (QPD) is a probability distribution that is directly parameterized by data. They were created to meet the need for easy-to-use continuous probability distributions flexible enough to represent a wide range of uncertainties, such as those commonly encountered in business, economics, engineering, and science.

How it works

Because QPDs are directly parameterized by data, they have the practical advantage of avoiding the intermediate step of parameter estimation, a time-consuming process that typically requires non-linear iterative methods to estimate probability-distribution parameters from data. Some QPDs have virtually unlimited shape flexibility and closed-form moments as well.

F^{-1} (y)= \left\{ \begin{array}{cl} L_0 & \text{for } y=0\\ \sum_{i=1}^n a_i g_i(y) & \text{for } 0 where \begin{array}{rcl} L_0 &=& \lim_{y\rarr 0^+} F^{-1}(y) \\ L_1 &=& \lim_{y\rarr 1^-} F^{-1}(y) \end{array} and the functions g_i(y) are continuously differentiable and linearly independent basis functions. Here, essentially, L_0 and L_1 are the lower and upper bounds (if they exist) of a random variable with quantile function F^{-1}(y) .

Impact

These distributions are called quantile-parameterized because for a given set of quantile pairs \{(x_i, y_i) \mid i=1,\ldots,n\} , where x_i=F^{-1}(y_i) , and a set of n basis functions g_i(y) , the coefficients a_i can be determined by solving a set of linear equations. If one desires to use more quantile pairs than basis functions, then the coefficients a_i can be chosen to minimize the sum of squared errors between the stated quantiles x_i and F^{-1}(y_i) .

Keelin and Powley illustrate this concept for a specific choice of basis functions that is a generalization of quantile function of the normal distribution, x=\mu+\sigma \Phi^{-1} (y) , for which the mean \mu and standard deviation \sigma are linear functions of cumulative probability y : \mu(y)=a_1+a_4 y \sigma(y)=a_2+a_3 y The result is a four-parameter distribution that can be fit to a set of four quantile/probability pairs exactly, or to any number of such pairs by linear least squares. Keelin and Powley call this the Simple Q-Normal distribution.

Some skewed and symmetric Simple Q-Normal PDFs are shown in the figures below. Differentiating x=F^{-1} (y)=\sum_{i=1}^n a_i g_i (y) with respect to y yields dx/dy . The reciprocal of this quantity, dy/dx , is the probability density function (PDF) f(y) = \left( \sum_{i=1}^n a_i {{d g_i(y)}\over{dy}} \right)^{-1} where 0 . Note that this PDF is expressed as a function of cumulative probability y rather than x . To plot it, as shown in the figures, vary y\in(0,1) parametrically. Plot x=F^{-1} (y) on the horizontal axis and f(y) on the vertical axis.

A function of the form of F^{-1} (y) is a feasible probability distribution if and only if f(y)>0 for all y \in (0,1) . This implies a feasibility constraint on the set of coefficients \boldsymbol a=(a_1,\ldots,a_n) \in \R^n : \sum_{i=1}^n a_i {{d g_i(y)}\over{dy}} >0 for all y \in (0,1) In practical applications, feasibility must generally be checked rather than assumed. A QPD's set of feasible coefficients S_\boldsymbol a=\{\boldsymbol a\in\R^n \mid \sum_{i=1}^n a_i d g_i (y)/dy > 0 for all y\in (0,1)\} is convex.

Because convex optimization requires convex feasible sets, this property simplifies optimization applications involving QPDs. The coefficients \boldsymbol a can be determined from data by linear least squares.

Given m data points (x_i,y_i) that are intended to characterize the CDF of a QPD, and m \times n matrix \boldsymbol Y whose elements consist of g_j (y_i) , then, so long as \boldsymbol Y^T \boldsymbol Y is invertible, coefficients' column vector \boldsymbol a can be determined as \boldsymbol a=(\boldsymbol Y^T \boldsymbol Y)^{-1} \boldsymbol Y^T \boldsymbol x , where m\geq n and column vector \boldsymbol x=(x_1,\ldots,x_m) .

If m=n , this equation reduces to \boldsymbol a=\boldsymbol Y^{-1} \boldsymbol x , where the resulting CDF runs through all data points exactly. An alternate method, implemented as a linear program, determines the coefficients by minimizing the sum of absolute distances between the CDF and the data subject to feasibility constraints. QPD transformations are governed by a general property of quantile functions: for any quantile function x=Q(y) and increasing function t(x), x=t^{-1} (Q(y)) is a quantile function.

For example, the quantile function of the normal distribution, x=\mu+\sigma \Phi^{-1} (y) , is a QPD by the Keelin and Powley definition. The natural logarithm, t(x)=\ln(x-b_l) , is an increasing function, so x=b_l+e^{\mu+\sigma \Phi^{-1} (y)} is the quantile function of the lognormal distribution with lower bound b_l . Importantly, this transformation converts an unbounded QPD into a semi-bounded QPD.

Similarly, applying this log transformation to the unbounded metalog distribution yields the semi-bounded (log) metalog distribution; likewise, applying the logit transformation, t(x)=\ln((x-b_l)/(b_u-x)) , yields the bounded (logit) metalog distribution with lower and upper bounds b_l and b_u , respectively. Moreover, by considering t(x) to be F^{-1} (y) distributed, where F^{-1} (y) is any QPD that meets Keelin and Powley's definition, the transformed variable maintains the above properties of feasibility, convexity, and fitting to data.

Such transformed QPDs have greater shape flexibility than the underlying F^{-1} (y) , which has n-2 shape parameters; the log transformation has n-1 shape parameters, and the logit transformation has n shape parameters. Moreover, such transformed QPDs share the same set of feasible coefficients as the underlying untransformed QPD. E[x^k] = \int_0^1 \left( \sum_{i=1}^n a_i g_i(y) \right)^k dy Whether such moments exist in closed form depends on the choice of QPD basis functions g_i (y) .

The unbounded metalog distribution and polynomial QPDs are examples of QPDs for which moments exist in closed form as functions of the coefficients a_i . Since the quantile function x=F^{-1}(y) is expressed in closed form, Keelin and Powley QPDs facilitate Monte Carlo simulation. Substituting in uniformly distributed random samples of y produces random samples of x in closed form, thereby eliminating the need to invert a CDF expressed as y=F(x) . The quantile function of the normal distribution, x=\mu+\sigma \Phi^{-1} (y) .

The quantile function of the Gumbel distribution, x=\mu - \beta \ln(-\ln(y)) . The quantile function of the Cauchy distribution, x=x_0+\gamma \tan[\pi(y-0.5)] . The quantile function of the logistic distribution, x=\mu+s \ln(y/(1-y) ) . The unbounded metalog distribution, which is a power series expansion of the \mu and s parameters of the logistic quantile function. The semi-bounded and bounded metalog distributions, which are the log and logit transforms, respectively, of the unbounded metalog distribution.

The SPT (symmetric-percentile triplet) unbounded, semi-bounded, and bounded metalog distributions, which are parameterized by three CDF points and optional upper and lower bounds. The Simple Q-Normal distribution The metadistributions, including the meta-normal Quantile functions expressed as polynomial functions of cumulative probability y , including Chebyshev polynomial functions. Like the SPT metalog distributions, the Johnson Quantile-Parameterized Distributions (JQPDs) are parameterized by three quantiles.

JQPDs do not meet Keelin and Powley's QPD definition, but rather have their own properties. JQPDs are feasible for all SPT parameter sets that are consistent with the rules of probability.

Text derived from https://en.wikipedia.org/w/index.php?oldid=1377024145 under CC BY-SA 4.0; modifications have been made.

Provenance

snapshot enwiki-001377024145 · captured 1790511967.0 · version history

Cite this page as: encyclopegia.org, “Quantile-parameterized distribution”, snapshot enwiki-001377024145. https://encyclopegia.org/a/quantile-parameterized-distribution

Sources cited in this revision

8 named source(s) extracted from the cited revision. A source with no author is shown by its publication; nothing is invented.