Classical and General Linear Modeling
Statistical
Our Statistical and Visualization framework provides a full suite of analytical and modeling tools for quantitative neuroscience and behavioral data.
We integrate classical statistics, Bayesian modeling, and data-driven inference with rich, publication-ready visualization pipelines — ensuring accuracy, interpretability, and transparency at every analytical stage.
We support a wide range of classical inferential statistics and regression-based models for both within- and between-subject analyses.
Supported analyses include:
- General Linear Model (GLM)
- Linear and Nonlinear Regression
- Mixed-Effects Models
- Non-Parametric Testing
- Post-hoc & Multiple Comparison Corrections
Bayesian and Hierarchical Modeling
Statistical
We employ Bayesian statistical frameworks for more flexible, uncertainty-aware inference across individual and group datasets.
Supported methods include:
- Bayesian Regression & ANOVA
- Hierarchical Bayesian Models
- MCMC & Variational Inference
- Model Evidence & Predictive Accuracy
Data Visualization & Reporting
Statistical
Our visualization pipeline converts complex statistical outcomes into clear, interpretable, and visually compelling figures.
Supported features include:
- Descriptive & Inferential Plots
- Advanced Visual Analytics
- Multivariate Visualization
- Interactive Dashboards
- Automated Reporting
Supported Environments & Libraries:
- Python: NumPy, SciPy, Statsmodels, PyMC, Matplotlib, Seaborn, Plotly
- R: tidyverse, ggplot2, lme4, brms, bayesplot
- MATLAB: traditional GLM and ANOVA workflows
- Integration: supports direct import/export from neuroimaging toolboxes (SPM, FSL, AFNI, MNE, FieldTrip).
