Sample size determination for three-level randomized clinical trials with randomization at the first or second level

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Clinical trials in the context of comparative effectiveness research (CER) are often conducted to evaluate health outcomes under real-world conditions and standard health care settings. In such settings, three-level hierarchical study designs are increasingly common. For example, patients may be nested within treating physicians, who in turn are nested within an urgent care center or hospital. While many trials randomize the third-level units (e.g., centers) to intervention, in some cases randomization may occur at lower levels of the hierarchy, such as patients or physicians. In this article, we present and verify explicit closed-form sample size and power formulas for three-level designs assuming randomization is at the first or second level. The formulas are based on maximum likelihood estimates from mixed-effect linear models and verified by simulation studies. Results indicate that even with smaller sample sizes, theoretical power derived with known variances is nearly identical to empirically estimated power for the more realistic setting when variances are unknown. In addition, we show that randomization at the second or first level of the hierarchy provides an increasingly statistically efficient alternative to third-level randomization. Power to detect a treatment effect under second-level randomization approaches that of patient-level randomization when there are few patients within each randomized second-level cluster and, most importantly, when the correlation attributable to second-level variation is a small proportion of the overall correlation between patient outcomes.

Original languageEnglish (US)
Pages (from-to)579-599
Number of pages21
JournalJournal of Biopharmaceutical Statistics
Volume24
Issue number3
DOIs
StatePublished - May 4 2014

Fingerprint

Sample Size Determination
Randomized Clinical Trial
Random Allocation
Randomisation
Sample Size
Randomized Controlled Trials
Comparative Effectiveness Research
Linear Mixed Effects Model
Likelihood Functions
Physicians
Small Sample Size
Treatment Effects
Ambulatory Care Facilities
Maximum Likelihood Estimate
Clinical Trials
Healthcare
Linear Models
Closed-form
Health
Proportion

Keywords

  • Cluster randomization
  • power
  • Sample size
  • Three-level data.

ASJC Scopus subject areas

  • Pharmacology (medical)
  • Pharmacology
  • Statistics and Probability
  • Medicine(all)

Cite this

@article{7452ae08144c499e93721a945d7a79ac,
title = "Sample size determination for three-level randomized clinical trials with randomization at the first or second level",
abstract = "Clinical trials in the context of comparative effectiveness research (CER) are often conducted to evaluate health outcomes under real-world conditions and standard health care settings. In such settings, three-level hierarchical study designs are increasingly common. For example, patients may be nested within treating physicians, who in turn are nested within an urgent care center or hospital. While many trials randomize the third-level units (e.g., centers) to intervention, in some cases randomization may occur at lower levels of the hierarchy, such as patients or physicians. In this article, we present and verify explicit closed-form sample size and power formulas for three-level designs assuming randomization is at the first or second level. The formulas are based on maximum likelihood estimates from mixed-effect linear models and verified by simulation studies. Results indicate that even with smaller sample sizes, theoretical power derived with known variances is nearly identical to empirically estimated power for the more realistic setting when variances are unknown. In addition, we show that randomization at the second or first level of the hierarchy provides an increasingly statistically efficient alternative to third-level randomization. Power to detect a treatment effect under second-level randomization approaches that of patient-level randomization when there are few patients within each randomized second-level cluster and, most importantly, when the correlation attributable to second-level variation is a small proportion of the overall correlation between patient outcomes.",
keywords = "Cluster randomization, power, Sample size, Three-level data.",
author = "Fazzari, {Melissa J.} and Kim, {Mimi Y.} and Moonseong Heo",
year = "2014",
month = "5",
day = "4",
doi = "10.1080/10543406.2014.888436",
language = "English (US)",
volume = "24",
pages = "579--599",
journal = "Journal of Biopharmaceutical Statistics",
issn = "1054-3406",
publisher = "Taylor and Francis Ltd.",
number = "3",

}

TY - JOUR

T1 - Sample size determination for three-level randomized clinical trials with randomization at the first or second level

AU - Fazzari, Melissa J.

AU - Kim, Mimi Y.

AU - Heo, Moonseong

PY - 2014/5/4

Y1 - 2014/5/4

N2 - Clinical trials in the context of comparative effectiveness research (CER) are often conducted to evaluate health outcomes under real-world conditions and standard health care settings. In such settings, three-level hierarchical study designs are increasingly common. For example, patients may be nested within treating physicians, who in turn are nested within an urgent care center or hospital. While many trials randomize the third-level units (e.g., centers) to intervention, in some cases randomization may occur at lower levels of the hierarchy, such as patients or physicians. In this article, we present and verify explicit closed-form sample size and power formulas for three-level designs assuming randomization is at the first or second level. The formulas are based on maximum likelihood estimates from mixed-effect linear models and verified by simulation studies. Results indicate that even with smaller sample sizes, theoretical power derived with known variances is nearly identical to empirically estimated power for the more realistic setting when variances are unknown. In addition, we show that randomization at the second or first level of the hierarchy provides an increasingly statistically efficient alternative to third-level randomization. Power to detect a treatment effect under second-level randomization approaches that of patient-level randomization when there are few patients within each randomized second-level cluster and, most importantly, when the correlation attributable to second-level variation is a small proportion of the overall correlation between patient outcomes.

AB - Clinical trials in the context of comparative effectiveness research (CER) are often conducted to evaluate health outcomes under real-world conditions and standard health care settings. In such settings, three-level hierarchical study designs are increasingly common. For example, patients may be nested within treating physicians, who in turn are nested within an urgent care center or hospital. While many trials randomize the third-level units (e.g., centers) to intervention, in some cases randomization may occur at lower levels of the hierarchy, such as patients or physicians. In this article, we present and verify explicit closed-form sample size and power formulas for three-level designs assuming randomization is at the first or second level. The formulas are based on maximum likelihood estimates from mixed-effect linear models and verified by simulation studies. Results indicate that even with smaller sample sizes, theoretical power derived with known variances is nearly identical to empirically estimated power for the more realistic setting when variances are unknown. In addition, we show that randomization at the second or first level of the hierarchy provides an increasingly statistically efficient alternative to third-level randomization. Power to detect a treatment effect under second-level randomization approaches that of patient-level randomization when there are few patients within each randomized second-level cluster and, most importantly, when the correlation attributable to second-level variation is a small proportion of the overall correlation between patient outcomes.

KW - Cluster randomization

KW - power

KW - Sample size

KW - Three-level data.

UR - http://www.scopus.com/inward/record.url?scp=84898941637&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898941637&partnerID=8YFLogxK

U2 - 10.1080/10543406.2014.888436

DO - 10.1080/10543406.2014.888436

M3 - Article

C2 - 24697506

AN - SCOPUS:84898941637

VL - 24

SP - 579

EP - 599

JO - Journal of Biopharmaceutical Statistics

JF - Journal of Biopharmaceutical Statistics

SN - 1054-3406

IS - 3

ER -