RepositoryCurrent collected state Current
Observed since 20 Oct, 17:59 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
PACKAGE EXPLORERView in registry
accmv
PyPIInference under the available complete-case missing value assumption
Versions collected1
Direct dependencies5From release 0.1.1
Last observed20 Oct, 17:59 UTC
README
Version 0.1.1 documentationaccmv
Python implementation of inverse-probability-weighted (IPW), regression-adjustment (RA), and multiply-robust (MR) inference under the available complete-case missing value assumption.
from accmv import estimate_single
fit = estimate_single(x, y, method="mr", n_boot=499, random_state=1)
print(fit.estimate, fit.conf_int)
For the paper's marginal linear model:
from accmv import fit_ipw_regression
# Shared with R: response/predictors use one-based y-column indices.
fit = fit_ipw_regression(x, y, response=2, predictors=(1,))
print(fit.coefficients)
If you use this software, please cite Cheng, Chen, Smith, and Zhao, “Handling Nonmonotone Missing Data with Available Complete-Case Missing Value Assumption” (paper).
Downloads & popularity
Awaiting observationsNo metric observations yet
Download counts and popularity will appear here as the collector receives them.
Versions 1
Collected releases| Version | Published | Direct dependencies | Open version |
|---|---|---|---|
| 0.1.1 | 19 Sept 2026 | 5 |
Package advisories
0No matching advisories collected
This describes our collected data; it is not a security assessment.
Repository
PENDINGMetadata history
Meaningful changesRecord identity
package:6ebe3dfe1703050e96e1d2043ce7ba75dbe6f63ebd73a22fb668040a55ae3ed8