Small-Sample Adjustments for Wald Tests Using Sandwich Estimators

Tests coefficients with sandwich estimator of variance and with small samples. Regression types supported are gee, linear regression, and conditional logistic regression.


Changes in version 0.9-6.1

  • had "fake" vignette, so removed .Rnw file. Now just pdf files in the /inst/doc/ directory.

Changes in version 0.9-6.0

  • Changed /inst/News.Rd to NEWS
  • changed help, no longer says it does Cox regression
  • modified mgee function so that if calls the gee function then geeUOmega. The previous method was clunky since it basically copied the code from gee and added some lines. Now I do it a better way by calling the gee function, then using it as an argument in the newly created geeUOmega function which inputs the output from gee. Changed help accordingly.

Changes in version 0.9-5.3

  • Changed print.saws file. It had an error when the test matrix was not p X p (where p=number of coefficients).

  • Removed dependence on survival. I hope to put adjustment for Cox proportional hazards in the future, but have not done it yet, so there is no dependence.

Changes in version 0.9-3.3

  • fix bug when the number of parameters is 1 (see dfCalc.R).

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


0.9-6.2 by Michael P. Fay, a year ago

Browse source code at

Authors: Michael P. Fay

Documentation:   PDF Manual  

Task views: Survival Analysis

GPL (>= 2) license

Depends on gee, stats

Suggests MASS

Suggested by geex.

See at CRAN