Chapter Contents |
Previous |
Next |

Examining Distributions |

A *cumulative distribution function* gives the
proportion of the data less than each possible value.
A *density function* is the derivative of the
cumulative distribution function.
*Density estimation* is the construction of an
estimate of the density function from the observed data.

Histograms are one type of density estimation. You can also plot the density function to construct density curves. Density curves are sometimes preferred because they do not contain the discontinuous steps present in histograms.

**Distribution ( Y )** provides two types of density estimation:
parametric and kernel.
In parametric estimation, the data are assumed to be from a
known parametric family of distributions.
The normal distribution is one of the most
commonly used parametric distributions.
Others include lognormal, exponential, and Weibull.

In kernel estimation, little is assumed about the functional form of the data. The data more completely determine the shape of the density curve. Kernel estimation is a type of nonparametric estimation.

Chapter Contents |
Previous |
Next |
Top |

Copyright © 1999 by SAS Institute Inc., Cary, NC, USA. All rights reserved.