BLIMP 3
Blimp 3 offers powerful latent variable modeling and imputation for incomplete data sets with up to three levels. Blimp's unique Bayesian computational architecture allows easy specification of complex analyses that are difficult or impossible to fit in other software packages.
BLIMP 3 FEATURES
- Bayesian estimation for regression, path, and latent variable models with up to three levels
- Missing data handling for normal, binary, ordinal, nominal variables, skewed continuous, and count variables.
- Missing data handling for interactive and nonlinear effects, including latent variable interactions
- Latent variables with random effects, interactions, nonlinear effects, and latent variable imputation
- Models for random variances (dynamic SEM, location/scale MLMs)
- Regression equations with embedded functions as predictors
- Fully conditional specification multiple imputation for single and multilevel models, latent response imputation for discrete variables
- Parameter constraints and auxiliary parameters that are functions of estimated model parameters
- Easy specification of selection and pattern mixture models for missing not at random processes
- Facilities for computing new variables with numerous built-in functions
- Rights and Sterba R-square effect sizes
BLIMP 3 DOWNLOAD
Blimp Studio features a tabbed interface that keeps the script and output file for each project together and organized. Blimp Studio automatically downloads new updates as they become available, so your software will always be current. The current version is 3.2.12.
- Download for Mac
- Download for Windows
- Download for Linux distributions
- OFFLINE INSTALLERS FOR MAC and windows
USER'S GUIDE
The User Guide provides an accessible overview of Blimp's simple scripting language, including dozens of new analysis examples covering regression models, path and latent variable models, psychometric models, multilevel models, and missing not at random models. All user examples are accessible and executable from Blimp Studio pull-down menus.
The research reported here was supported by the Institute of Education Sciences, U.S. Department of Education, through Grant R305D150056 & R305D190002 to UCLA. The opinions expressed are those of the authors and do not represent views of the Institute or the U.S. Department of Education.
Craig Enders, PI
Brian Keller, Co-PI
Han Du, Co-PI
Roy Levy, Co-PI
