CaseCenteredLogisticWeightedSas: Conduct case-centered analysis for weighted risk sets via SAS

In kaz-yos/distributed: Examine Privacy Preserving Data Analysis Methods in Simulated Distributed Data Network

Description

Given a specifically formatted weighted data frame, conduct case-centered analysis by weighted individual-level data reconstruction. This command calls unix-style sas command. If sas is not available, it will stop with an error.

Usage

CaseCenteredLogisticWeightedSas(df, method, strata)

Arguments

df	data frame containing one row for each riskset with the following variables: events_A1 (event count among the exposed), events_A0 (event count among the unexposed), riskset_A1 (total count among the exposed including those who are having events), and riskset_A0 (total count among the unexposed including those who are having events). The data frame additionally must contain valid weighted versions of these variables (w_events_A1, etc) and variance of weights for four types of cells defined by event and exposure status (varw_events_A* and varw_nonevents_A*), approximate weighted analysis is conducted.
method	Either efron or breslow
strata	Specify space-deliminated names of stratifying variables.

Value

sasfit object with coef and vcov methods.

Author(s)

Kazuki Yoshida

kaz-yos/distributed documentation built on May 27, 2019, 4:50 a.m.