世界上最受歡迎的精確統計軟體─最新版本

StatXact主要是處理無母數統計推論，可處理多種資料類型:連續的、類別的、多維度的資料都可，即使樣本很小、很離散或是偏態嚴重，分析出來的結果仍可信。

更新介紹

StatXact® 12 Presents Over 160 Tests and Procedures for Exact Inference
StatXact® 12 provides statisticians in disciplines across the social and natural sciences with the world’s most expansive toolkit for exact inference and power analysis. Offering more than 160 tests and procedures, the StatXact® suite has transformed the complex algorithms of modern statistical analysis into a validated software package with a user-friendly interface.

The Advantages of StatXact 12
StatXact offers more tests and procedures for exact inference and power analysis than any other software package on the market. Fast and accurate inferences are compiled on an easy-to-use interface, drawing on complex algorithms created by Cytel’s team of statistical experts.

Our experts are constantly developing new types of exact tests, broadening the selection of calculations available to our users. Many of these methods are only available to StatXact users, and have received acclaim for their performance from both industry and academia.

The Benefits of StatXact 12

 Empower
Play a more strategic role in your organization: Perform fast and accurate hypothesis-testing that is responsive to an array of trial needs. Obtain reliable results for smaller sample sizes, allowing for timely and cost-effective trials. Redirect time, attention and critical resources to other vital aspects of study success.

 Trust
StatXact has harnessed the immense power of Cytel’s nonparametric and exact inference methods to make enduring contributions to the fields across the natural and social sciences, receiving acclaim from both industry and academia for its high quality performance of complex calculations.

 Share
StatXact simplifies tests that normally require complex calculation. Findings that should be difficult to compute are easy to identify and communicate.

 Assess
Access StatXact’s selection of exact and Monte Carlos tests to increase the statistical power of trial results. Unnecessary risks associated with conventional (asymptotic) testing are curtailed using performance software that is fast and accurate.

The Features of StatXact 12

The Toolkit
Not only does StatXact provide more tests and procedures for exact and power analysis than any other software currently on the market, but many of these complex tests are only available to StatXact users. These exclusive features include exact tests for correlated two samples data, exact power and sample size computations for binomial and multinomial data, and exact tests for equivalence and non-inferiority of paired and independent binomial data. Users of StatXact and LogXact can also request an Exact crossover module for a 2x2 crossover trial.

New Developments
Statisticians at Cytel are continuously developing new algorithms that offer users even more sophisticated methods of exact-testing. Innovations in StatXact 12  include:

• Multiple endpoints procedure with gatekeeping
• Pesarin-Salmaso nonparametric combination test for multivariate data
• Super-superiority test for two independent binomials
• New asymptotic confidence interval methods for two independent binomials
• Unconditional test of odds ratio for two independent binomials
• Parameter estimation for stratified 2-sample binomials
• Exact analysis of 1-sample and 2-sample negative binomial data
• Exact power and sample size computation for 1-sample and 2-sample negative binomial data
• Exact power and sample size computation for 1-sample and 2-sample Poisson data

Exact Tests for Continuous Data
StatXact features a range of exact and Monte Carlo tests for one-sample, two-sample and k-sample data (independent and blocked).

Exact Tests for Categorical Data
StatXact performs exact tests for both independent and correlated categorical data. It can compute tests for stratified Poisson samples, and is the only product on the market that delivers sample size and power calculations for binomial and multinomial distributions. StatXact 12 provides additional nonparametric inference tests for categorical data, and adds to existing coefficient options for correlated categorical data.