. 2017 Jul;107(7):1078–1086. doi: 10.2105/AJPH.2017.303707

TABLE 1—

Summary of Known Functions and Procedures for Analyzing Group-Randomized Trials (GRTs) via the Methods Described for Three Commonly Used Software Programs

	Software
Method	SAS	Stata	R
Outcome analysis of all available data
Mixed-effects models	PROC MIXED	mixed	lme4
	PROC NLMIXED	melogit	nlme
	PROC GLIMMIX	mepoisson
GEE	PROC GENMOD^a	xtgee	geepack/geeM
tMLE	NA	NA	NA^b
QIF	%qif	NA	qif^c
Permutation tests	%ptest	NA	NA
Accounting for missing outcomes
Multiple imputation for clustered data	%mmi_impute^d	REALCOM-IMPUTE	pan
Multiple imputation for clustered data	%mmi_analyze	mi impute^d	jomo^e
Inverse probability weighting	PROC GENMOD^f	NA^g	CRTgeeDR
Causal inference–based methods^h
AU-GEE	NA	NA	CRTgeeDR
Doubly robust AU-GEE	NA	NA	CRTgeeDR

Note. AU-GEE = augmented GEE; GEE = generalized estimating equations; NA = not applicable; QIF = quadratic inference function; tMLE = targeted maximum likelihood.

^{^a}

PROC GEE is another option, but it is in the experimental phase and has limited usefulness for GRTs over and above PROC GENMOD.

^{^b}

In R, tmle is available for tMLE; at the time of writing, however, it did not allow for clustering.

^{^c}

At the time of writing, we were unable to load the package, and it allows only equal cluster sizes; however, Westgate modified the code for GRTs with variable cluster sizes in the appendix of his article.⁶³

^{^d}

Only useful for continuous outcomes.

^{^e}

In R, mice is available for multiple imputation; at the time of writing, however, it did not account for clustering.

^{^f}

Cannot account for imprecision in weights.

^{^g}

xtgee cannot accommodate individual-level weights but, rather, only group-specific weights.

^{^h}

The 2 listed methods are related: AU-GEE accounts for baseline covariate imbalance, and doubly robust AU-GEE, an extension of AU-GEE, accounts for both baseline covariate imbalance and missing data.