samplics svy · svylab.com
redirecting in 12s

This library is archived. Active development, new features, and long-term support have moved to svy. This page is preserved for citation and historical reference.

Migration Notice — 2025

samplics has grown
into svy

What began as samplics — a Python library for design-based survey analysis — has evolved into a broader, more capable ecosystem. svy and svyLab supersede samplics with a cleaner API, expanded methodology, and active long-term support.


samplics topic
svy documentation
Sample size calculation & allocation
Sample selection (SRS, SYS, PPS, multi-stage)
Weight adjustment & nonresponse
Poststratification, calibration, raking
Replicate weights (Bootstrap, BRR, Jackknife)
Taylor & replicate-based estimation
Categorical analysis & tabulation
Generalized Linear Models (GLMs) &
Small area estimation (Fay-Herriot, EBLUP)

pip install svy  ·  Full docs at svylab.com/docs


If you use samplics in published research, please cite the original JOSS paper. For work using svy, citation details are available in the svy documentation.

Diallo, M.S. (2021). samplics: a Python Package for Selecting, Weighting and Analyzing Data from Complex Sampling Designs. Journal of Open Source Software, 6(68), 3376.

📄 doi:10.21105/joss.03376
@article{Diallo2021,
  author  = {Diallo, Mamadou S.},
  title   = {samplics: a Python Package for Selecting,
             Weighting and Analyzing Data from Complex
             Sampling Designs},
  journal = {Journal of Open Source Software},
  year    = {2021},
  volume  = {6},
  number  = {68},
  pages   = {3376},
  doi     = {10.21105/joss.03376},
  url     = {https://doi.org/10.21105/joss.03376}
}

🧱
Cleaner API
A unified Sample object replaces samplics' fragmented class structure. One design, one object, full workflow.
📐
Expanded methods
GLMs, small area estimation, replicate weight variance, and data I/O (SPSS, Stata, SAS) via svy-io and svy-sae.
Modern stack
Built for Python 3.11+, Polars-native, with pandas compatibility. Faster and memory-efficient on large survey datasets.
🔬
Validated against R
Estimates validated against R's survey package. Read the validation study →
Redirecting to svylab.com/docs in 12s