TOPICS
Search

Shape Parameter


A shape parameter changes the shape of a family of statistical distributions rather than merely shifting it through a location parameter or rescaling it through a scale parameter. For example, the Weibull distribution has distribution function

 F(x;k,lambda)=1-e^(-(x/lambda)^k)

for x>=0, with F(x;k,lambda)=0 for x<0. Here k>0 is a shape parameter and lambda>0 is a scale parameter. Setting k=1 gives the exponential distribution.

A family can have more than one shape parameter. The stable distribution has both an index of stability alpha and a skewness parameter beta.


See also

Exponential Distribution, Index of Stability, Location Parameter, Scale Parameter, Skewness Parameter, Stable Distribution, Weibull Distribution

Explore with Wolfram|Alpha

References

National Institute of Standards and Technology. "Families of Distributions." §1.3.6.3 in NIST/SEMATECH e-Handbook of Statistical Methods. https://www.itl.nist.gov/div898/handbook/eda/section3/eda363.htm.National Institute of Standards and Technology. "Weibull Distribution." §1.3.6.6.8 in NIST/SEMATECH e-Handbook of Statistical Methods. https://www.itl.nist.gov/div898/handbook/eda/section3/eda3668.htm.Nolan, J. P. Univariate Stable Distributions: Models for Heavy Tailed Data. Cham, Switzerland: Springer, 2020. https://doi.org/10.1007/978-3-030-52915-4.

Cite this as:

Weisstein, Eric W. "Shape Parameter." From MathWorld--A Wolfram Resource. https://mathworld.wolfram.com/ShapeParameter.html

Subject classifications