# library.univar Submodule¶

## Module Summary¶

Interfaces for the NAG Mark 29.0 univar Chapter.

univar - Univariate Estimation

This module deals with the estimation of unknown parameters of a univariate distribution. It includes both point and interval estimation using maximum likelihood and robust methods.

naginterfaces.library.examples.univar :

This subpackage contains examples for the univar module. See also the Examples subsection.

## Functionality Index¶

2 sample -test: ttest_2normal()

Confidence intervals for parameters

binomial distribution: ci_binomial()

Poisson distribution: ci_poisson()

Maximum likelihood estimation of parameters

Normal distribution, grouped and/or censored data: estim_normal()

Weibull distribution: estim_weibull()

Outlier detection

Peirce

raw data or single variance supplied: outlier_peirce_1var()

two variances supplied: outlier_peirce_2var()

Parameter estimates

generalized Pareto distribution: estim_genpareto()

Robust estimation

confidence intervals

median, median absolute deviation and robust standard deviation: robust_1var_median()

-estimates for location and scale parameters

standard weight functions: robust_1var_mestim()

trimmed and winsorized means and estimates of their variance: robust_1var_trimmed()

user-defined weight functions: robust_1var_mestim_wgt()

For full information please refer to the NAG Library document

https://www.nag.com/numeric/nl/nagdoc_29/flhtml/g07/g07intro.html

## Examples¶

naginterfaces.library.examples.univar.estim_weibull_ex.main()[source]

Maximum likelihood estimates for parameters of the Weibull distribution.

>>> main()
naginterfaces.library.univar.estim_weibull Python Example Results.
Maximum likelihood estimates for parameters of the Weibull distribution.
beta^ =    -2.1073, standard error =     0.4627
gamma^ =     2.7870, standard error =     0.4273