Java Statistical Classes

This document is the API specification for the Java Statistical Classes (JSC) library, version 1.0.

See:
Description

Packages

jsc	Provides classes to support the development of statistical software.
jsc.ci	Provides classes and interfaces concerned with confidence intervals.
jsc.combinatorics	Provides combinatorial objects and algorithms that are useful in probability and statistics.
jsc.contingencytables	Provides classes concerned with the analysis of contingency tables.
jsc.correlation	Provides classes to calculate and test correlation coefficients.
jsc.curvefitting	Provides classes to fit curves to data.
jsc.datastructures	Provides classes for some data structures useful in statistics.
jsc.descriptive	Provides classes to calculate descriptive statistics.
jsc.distributions	Provides classes to represent statistical distributions.
jsc.event	Provides classes and interfaces that define statistical and sampling events.
jsc.goodnessfit	Provides classes to calculate and test goodness-of-fit.
jsc.independentsamples	Provides classes and interfaces concerned with frequentist inference for independent samples.
jsc.mathfunction	Provides classes for the parsing, evaluation and differentiation of mathematical expressions at run-time.
jsc.numerical	Provides classes to implement various numerical methods.
jsc.onesample	Provides classes and interfaces concerned with frequentist inference for single samples, or paired samples that can be reduced to single samples by taking differences.
jsc.regression	Provides classes to perform regression analyses.
jsc.relatedsamples	Provides classes and interfaces concerned with frequentist inference for related samples.
jsc.statistics	Provides interfaces that define various statistics.
jsc.swt	Statistical Windowing Toolkit provides classes to support the building of graphical user interfaces for statistical applications.
jsc.swt.accessory	Provides classes to create user interface accessories for statistical applications.
jsc.swt.control	Provides classes to create various user controls for statistical applications.
jsc.swt.datatable	Provides classes to enter, edit and display tabular data and output.
jsc.swt.dialogue	Provides classes to create dialogue windows for statistical applications.
jsc.swt.file	Provides classes that support file handling for statistical applications.
jsc.swt.help	Provides classes to create help windows for statistical applications.
jsc.swt.mdi	Provides classes to create applications with multiple document interfaces.
jsc.swt.menu	Provides classes to create various common menus and menu items for statistical applications.
jsc.swt.panel	Provides classes to create various panels.
jsc.swt.plot	Provides classes and interfaces that support plotting.
jsc.swt.plot2d	Provides classes to create various plots.
jsc.swt.text	Provides classes for handling text and numbers.
jsc.swt.util	Provides various classes to support statistical applications.
jsc.swt.virtualgraphics	Provides classes to enable drawing and plotting in a virtual (world) co-ordinate system.
jsc.tests	Provides classes and interfaces concerned with significance tests.
jsc.util	Provides various methods to support statistical calculations and plotting.

This document is the API specification for the Java Statistical Classes (JSC) library, version 1.0.

JSC provides classes to support the development of software for the statistical analysis of data, statistical simulations, and software to teach statistics. Many classes could also be of use generally in non-statistical applications.

Unlike most statistical software libraries, JSC provides more than numerical algorithms. JSC takes advantage of Java's platform-independent graphics to provide a comprehensive toolkit for creating statistical plots and graphical user interfaces for statistical applications.

The standard libraries of Java provide many features that are likely to be useful in statistical applications; such as mathematical functions, data structures, tables, file handling, graphics and interface components. Some of these libraries, particularly those concerned with graphics and interface components, are complex and difficult for the beginner. JSC avoids this difficulty by providing Java components specifically designed for building statistical applications. These provide all the high-level graphics you would expect, such as histograms, boxplots and scatterplots; and low-level graphics that allow you to easily build your own graphical displays by plotting in a natural coordinate system. JSC also provides simplified versions of Java's interface components; such as menus, sliders, dialogue boxes; and ready-made high-level components such as data windows similar to those found in statistical packages.

JSC supplements Java's mathematical functions with basic functions and operations useful to the statistician; such as ranking, combinatorics, gamma and beta functions; and provides procedures for evaluating and differentiating mathematical functions input by the user.

Most important of all, JSC provides an extensive library of reliable statistical algorithms covering many areas of statistics: including descriptive, traditional, non-parametric, multivariate, resampling and Bayesian statistics; curve fitting and regression; distributions and random number generation. These are supported by classes of general numerical algorithms with statistical relevance; such as quadrature, optimization, root finding and numerical linear algebra.