What is Stat-Ease 360?
Achieve revolutionary enhancements to your product and process using Stat-Ease 360. This upgraded "pro" edition enhances the Design-Expert software with potent features tailored for advanced users. Leveraging the same efficient workflow that establishes Design-Expert as a premier choice for experimental design, technical experts engaged in computer-based experiments or those interested in integrating Python scripting can now fully utilize the array of novel functionalities. These include space-filling designs, Gaussian process models, Python scripting capabilities, and an additional logistic classification node. This transforms Stat-Ease 360 into a more robust iteration of Design-Expert.
The 2022 Release introduces new features such as Custom Graphs, a comprehensive Analysis Summary for multiple responses, the capability to assess blocks as random effects, and a straightforward Import/Export function for Excel files, expediting data transfer. With Stat-Ease 360, the application of potent multifactor testing tools becomes exceptionally straightforward.
Why Stat-Ease 360?
Design Your Experiment: Plan your optimal experiments effortlessly through integrated power calculations, along with the flexibility to incorporate blocks and center points. The presence of design wizards and user-friendly interfaces ensures that the process is considerably simpler than you might have envisioned.
Analyze Your Data: Effortlessly identify statistical significance and determine the most accurate method to model your results. Acquire the necessary confidence to effectively present or even publish your findings.
Visualize Your Results: Select from an extensive array of graphs designed to pinpoint noteworthy effects and vividly represent your outcomes. These visual outputs leave a lasting impact when conveying your findings to supervisors and colleagues.
Features of Stat-Ease 360
Factorial Designs: Factorial designs involve systematically studying the combined effects of multiple factors on a response variable in Design of Experiments.
RSM Designs: Response Surface Methodology (RSM) designs involve creating mathematical models to predict and optimize responses based on multiple variables.
Mixture & Combined Designs: Mixture and combined designs focus on optimizing variables when components are mixed or combined.
Space-filling Designs: Space-filling designs aim to efficiently sample the experimental space to ensure thorough exploration of variables.
Design Evaluation Tools: Design evaluation tools encompass various techniques and analyses used to assess the quality, efficiency, and effectiveness of experimental designs.
ANOVA, logistic & Poisson regression: ANOVA (Analysis of Variance), logistic regression, and Poisson regression are statistical techniques used to analyze experimental data and model relationships between variables.
Gaussian Process Models: Gaussian Process Models are statistical models used to describe the relationships between variables and predict outcomes while considering uncertainty.
Diagnostic Plots: Diagnostic plots are graphical representations used to identify patterns, outliers, and potential issues within experimental data.
3D graphics: 3D graphics in the context of Design of Experiments refer to three-dimensional visual representations used to depict the relationships and interactions between multiple variables and responses, providing a comprehensive view of experimental outcomes.
Numerical Optimization: Numerical optimization involves using mathematical algorithms to find the best combination of input variables that maximizes or minimizes a specific objective function, helping to identify optimal experimental conditions.
Python Integration: Incorporate Python programming language functionalities and scripts into a software or system, to enhance and customize the software's behavior, perform complex analyses, or extend its capabilities using Python code.
How Stat-Ease 360 helps you?
Design:
- Factorial and fractional-factorial designs, encompassing minimum-run designs, as well as efficient multi-level configurations.
- Incorporating response surface designs such as central composite and Box-Behnken, ensuring optimality.
- Inclusive of mixture designs spanning screening, simplex, and optimal formulations.
- Crafting custom optimal combined designs tailored for mixture-process scenarios, double-mixture setups, and mixture-amount conditions.
- Integrating split-plot designs for factorial arrangements, response surface investigations, and combined mixture-process explorations.
Design Augmentation:
- Duplication, blocking, and center points inclusion.
- Incorporation of foldover, semi-foldover, and optimal expansion strategies.
- Tailored enhancement through custom augmentation involving design space adjustments such as shifting, expansion, or contraction.
Analysis:
- Assessment tools for designs encompassing standard error and fraction of design space (FDS).
- A summary table for comparing models, along with various methods for model reduction.
- Comprehensive analysis summary featuring ANOVA, Poisson regression, logistic regression, restricted maximum likelihood, and additional techniques.
- Diagnostic tools for residuals and influence graphs, incorporating a Box-Cox plot for transformation analysis.
- Inclusion of error propagation (POE) capabilities.
Graphics:
- Single-factor and multi-factor profiling, interaction assessment, contour mapping, 3D surface visualization, cube plotting, and perturbation/trace graphing.
- Displaying data through 2D and 3D scatterplots, histograms, box plots, as well as personalized graphs tailored for analysis representation.
Post-Analysis:
- Utilization of both numerical and graphical optimization, accompanied by choices for confidence intervals.
- Enabling point prediction and analysis of confirmation runs.
Miscellaneous:
- Incorporate Python for customizable programming integration.
- Analyze random blocks systematically.
- Effortlessly import and export data to and from Excel files.
- Implement space-filling designs featuring Gaussian process models for computer-based experiments.
- Utilize threshold and ROC curves for logistic classification.
What's New?
Analysis Summary: The enhanced Analysis Summary extends the former Coefficients Table by incorporating additional model-fit metrics. Effortlessly observe p-values, R-squares, model equations, and other relevant information across all response variables.
Custom Graphs: The Graph Columns node has undergone an enhancement and is now known as Custom Graphs. This updated feature allows you to create plots for analysis data, such as predicted values and residuals. Additionally, you have the ability to differentiate data points using varying sizes and symbols.
Hosted Network Licensing: An additional licensing choice has been introduced, enabling the hosting of a network license at statease.com. This option grants you the capability to operate the software on numerous devices without necessitating an on-site license server, ultimately leading to cost savings in terms of self-managed software deployment and administration.
Stat-Ease 360 Training?
Discover the principles of Design of Experiments (DOE) in a manner that suits your learning style best! Guided by specialists from Factonity in the field of DOE, our training, which is centered around real case studies, enhances and tailors your learning journey for maximum effectiveness.
We offer following trainings: