crtrest: A command for ratio estimators of intervention effects on event rates in cluster randomized trials

Xiangmei Ma; Yin Bun Cheung

doi:10.1177/1536867X221141012

crtrest: A command for ratio estimators of intervention effects on event rates in cluster randomized trials

Xiangmei Ma, Yin Bun Cheung

Research output: Contribution to journal › Article › Scientific › peer-review

Abstract

We describe five asymptotically unbiased estimators of intervention effects on event rates in nonmatched and matched-pair cluster randomized trials, and we present a bias-corrected version of the estimators for use when the number of clusters is small. The estimators are the ratio of mean counts (r₁), ratio of mean cluster-level event rates (r₂), ratio of event rates (r₃), double ratio of counts (r₄), and double ratio of event rates (r₅). r₁, r₂, and r₃ estimate the total effect, which comprises the direct and indirect effects; r₄ and r₅ estimate the direct effect. We describe a new command, crtrest, that provides these ratio estimators and their standard errors in nonmatched and matched-pair cluster randomized trials.

Original language	English
Pages (from-to)	908-923
Number of pages	16
Journal	STATA JOURNAL
Volume	22
Issue number	4
DOIs	https://doi.org/10.1177/1536867X221141012
Publication status	Published - 2022
Publication type	A1 Journal article-refereed

Keywords

cluster randomized trial
crtrest
event rate
intervention effects
ratio estimator
st0695

Publication forum classification

Publication forum level 1

ASJC Scopus subject areas

Mathematics (miscellaneous)

Access to Document

10.1177/1536867X221141012

Cite this

@article{abe35aa2612548f787e0cb43c75d0f64,

title = "crtrest: A command for ratio estimators of intervention effects on event rates in cluster randomized trials",

abstract = "We describe five asymptotically unbiased estimators of intervention effects on event rates in nonmatched and matched-pair cluster randomized trials, and we present a bias-corrected version of the estimators for use when the number of clusters is small. The estimators are the ratio of mean counts (r1), ratio of mean cluster-level event rates (r2), ratio of event rates (r3), double ratio of counts (r4), and double ratio of event rates (r5). r1, r2, and r3 estimate the total effect, which comprises the direct and indirect effects; r4 and r5 estimate the direct effect. We describe a new command, crtrest, that provides these ratio estimators and their standard errors in nonmatched and matched-pair cluster randomized trials.",

keywords = "cluster randomized trial, crtrest, event rate, intervention effects, ratio estimator, st0695",

author = "Xiangmei Ma and Cheung, \{Yin Bun\}",

note = "Funding Information: We thank the anonymous reviewer for helpful comments. This work was supported by the National Medical Research Council, Singapore (MOH-000526). Publisher Copyright: {\textcopyright} StataCorp LLC 2022.",

year = "2022",

doi = "10.1177/1536867X221141012",

language = "English",

volume = "22",

pages = "908--923",

journal = "STATA JOURNAL",

issn = "1536-867X",

publisher = "SAGE Publications Inc.",

number = "4",

}

TY - JOUR

T1 - crtrest

T2 - A command for ratio estimators of intervention effects on event rates in cluster randomized trials

AU - Ma, Xiangmei

AU - Cheung, Yin Bun

N1 - Funding Information: We thank the anonymous reviewer for helpful comments. This work was supported by the National Medical Research Council, Singapore (MOH-000526). Publisher Copyright: © StataCorp LLC 2022.

PY - 2022

Y1 - 2022

N2 - We describe five asymptotically unbiased estimators of intervention effects on event rates in nonmatched and matched-pair cluster randomized trials, and we present a bias-corrected version of the estimators for use when the number of clusters is small. The estimators are the ratio of mean counts (r1), ratio of mean cluster-level event rates (r2), ratio of event rates (r3), double ratio of counts (r4), and double ratio of event rates (r5). r1, r2, and r3 estimate the total effect, which comprises the direct and indirect effects; r4 and r5 estimate the direct effect. We describe a new command, crtrest, that provides these ratio estimators and their standard errors in nonmatched and matched-pair cluster randomized trials.

AB - We describe five asymptotically unbiased estimators of intervention effects on event rates in nonmatched and matched-pair cluster randomized trials, and we present a bias-corrected version of the estimators for use when the number of clusters is small. The estimators are the ratio of mean counts (r1), ratio of mean cluster-level event rates (r2), ratio of event rates (r3), double ratio of counts (r4), and double ratio of event rates (r5). r1, r2, and r3 estimate the total effect, which comprises the direct and indirect effects; r4 and r5 estimate the direct effect. We describe a new command, crtrest, that provides these ratio estimators and their standard errors in nonmatched and matched-pair cluster randomized trials.

KW - cluster randomized trial

KW - crtrest

KW - event rate

KW - intervention effects

KW - ratio estimator

KW - st0695

U2 - 10.1177/1536867X221141012

DO - 10.1177/1536867X221141012

M3 - Article

AN - SCOPUS:85146004648

SN - 1536-867X

VL - 22

SP - 908

EP - 923

JO - STATA JOURNAL

JF - STATA JOURNAL

IS - 4

ER -

crtrest: A command for ratio estimators of intervention effects on event rates in cluster randomized trials

Abstract

Keywords

Publication forum classification

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this