TVEM SAS Macro for Estimating a Time-Varying Effect Model

Our software resources are permanently archived at TVEM is no longer supported by the Help Desk. For the latest software and research updates, visit Stephanie Lanza’s website on TVEM and addictive substances research.

SAS TVEM Macro + Examples:
Users’ Guide: %TVEM SAS Macro Users’ Guide (Version 3.1.1)
TVEM Macro for ZIP outcomes:


For use with SAS Version 9.2 or higher for Windows.

The TVEM SAS macro estimates coefficients in a time-varying effect model. Traditional analytic methods assume that covariates have constant (i.e., time-invariant) effects on a time-varying outcome. The %TVEM macros are able to estimate the time-varying effects of covariates. TVEM is a convenient tool for several types of data.

4-minute video: How to run a SAS macro

Features of the TVEM SAS macro

  • Option to include multiple non-time-varying covariates
  • Option to include multiple time-varying covariates
  • Ability to accommodate of different distributions (normal, logistic, or Poisson) measured over time
  • Option to employ a penalized truncated power spline basis instead of a B-spline basis function
  • Ability to model within-subject correlation using random effects or a robust sandwich variance estimator New in version 3.1.0
  • Enhanced screen output for improved interpretability New in version 3.1.0
  • Multiple optional output datasets New in version 3.1.0

The %TVEM_zip for outcomes (v 2.1.1) is available separately to fit zero-inflated Poisson models.


Recommended Citations

TVEM SAS Macro (Version 3.1.1) [Software]. (2017). University Park: The Methodology Center, Penn State. Retrieved from

Li, R., Dziak, J. J., Tan, X., Huang, L., Wagner, A. T., & Yang, J. (2017). TVEM (time-varying effect model) SAS macro users’ guide (Version 3.1.1). University Park: The Methodology Center, Penn State. Retrieved from