BLIMP 4
Blimp 4 offers powerful latent variable modeling for data sets with up to three levels. Its unique MCMC architecture enables simple specification of complex analyses that are difficult or impossible to fit in other software. Missing data handling is built into every analysis. Up to a 3x speed increase from version 3, and full R integration with the rblimp package.
BLIMP 4 FEATURES
- Regression and latent variable models with up to three levels
- R integration with the rblimp package
- Generalized linear and generalized linear mixed models for binary, ordinal, multicategorical, and count outcomes
- Skewed manifest and latent variables using the Yeo–Johnson transformation
- Mediation, moderated mediation, and mediation with discrete mediators and outcomes
- Latent variable interactions with manifest and categorical moderators
- Three-way and higher-order latent variable interactions
- Psychometric models and moderated nonlinear factor analysis
- Multilevel models with heterogeneous variation and location-scale models
- Dynamic multilevel SEM with lagged effects
- Residualized effects for random-intercept cross-lagged panel models
- Sum score predictors with item-level missing data handling
- Selection models and pattern mixture models for MNAR missingness
- Two-part models for zero inflation and floor or ceiling effects
BLIMP 4 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 4.0. A detailed installation guide is available here.
USER'S GUIDE
The User Guide provides an accessible overview of Blimp's simple scripting language, including dozens of new analysis examples covering linear regression and generalized linear regression models, latent variable models, multilevel models, models for longitudinal and intensive repeated measures data, and many more. All user examples are accessible and executable from the Examples pull-down menu in Blimp Studio.
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
