{{Short description|Kind of numerical parameter of a parametric family of probability distributions}} In probability theory and statistics, a '''shape parameter''' (also known as '''form parameter''')<ref>{{Cite journal |last=Ekawati |first=Dian |last2=Warsono |last3=Kurniasari |first3=Dian |date=December 2014 |title=On the Moments, Cumulants, and Characteristic Function of the Log-Logistic Distribution |url=http://repository.lppm.unila.ac.id/120/1/23%20On%20the%20Moments,%20Cumulants,%20and%20Characteristic%20Function%20of%20the%20Log-Logistic%20Distribution.pdf |journal=The Journal for Technology and Science |volume=25}}</ref> is a kind of numerical parameter of a parametric family of probability distributions<ref>Everitt B.S. (2002) Cambridge Dictionary of Statistics. 2nd Edition. CUP. {{isbn|0-521-81099-X}}</ref> that is neither a location parameter nor a scale parameter (nor a function of these, such as a rate parameter). Such a parameter must affect the {{em|shape}} of a distribution rather than simply shifting it (as a location parameter does) or stretching/shrinking it (as a scale parameter does). For example, {{gloss|peakedness}} refers to how round the main peak is.<ref name="Birnbaum 1948 pp. 76–81">{{cite journal | last=Birnbaum | first=Z. W. | title=On Random Variables with Comparable Peakedness | journal=The Annals of Mathematical Statistics | publisher=Institute of Mathematical Statistics | volume=19 | issue=1 | year=1948 | issn=0003-4851 | doi=10.1214/aoms/1177730293 | pages=76–81| doi-access=free }}</ref> [[Image:Standard symmetric pdfs.svg|300px|thumb|Probability density functions for selected distributions with mean 0 and variance 1.]]
==Estimation== Many estimators measure location or scale; however, estimators for shape parameters also exist. Most simply, they can be estimated in terms of the higher moments, using the method of moments, as in the ''skewness'' (3rd moment) or ''kurtosis'' (4th moment), if the higher moments are defined and finite. Estimators of shape often involve higher-order statistics (non-linear functions of the data), as in the higher moments, but linear estimators also exist, such as the L-moments. Maximum likelihood estimation can also be used.
==Examples== The following continuous probability distributions have a shape parameter: * Beta distribution * Burr distribution * Dagum distribution * Erlang distribution * ExGaussian distribution * Exponential power distribution * Fréchet distribution * Gamma distribution * Generalized extreme value distribution * Log-logistic distribution * Log-t distribution * Inverse-gamma distribution * Inverse Gaussian distribution * Pareto distribution * Pearson distribution * Skew normal distribution * Lognormal distribution * Student's t-distribution * Tukey lambda distribution * Weibull distribution By contrast, the following continuous distributions do ''not'' have a shape parameter, so their shape is fixed and only their location or their scale or both can change. It follows that (where they exist) the skewness and kurtosis of these distribution are constants, as skewness and kurtosis are independent of location and scale parameters. * Exponential distribution * Cauchy distribution * Logistic distribution * Normal distribution * Raised cosine distribution * Uniform distribution * Wigner semicircle distribution
==See also== * Skewness * Kurtosis * Location parameter
==References== <references/>
{{Statistics|inference}}
Category:Statistical parameters