Switching cluster membership in cluster randomized control trials: Implications for design and analysis
Jonathan D Schweig1, John F Pane1, Daniel F McCaffrey2
1RAND Corporation.
Psychological Methods
|April 10, 2020
Summary
Cluster-randomized trials (CRTs) with noncompliance require careful analysis. Using linear regression with two-way cluster adjusted standard errors provides unbiased intent-to-treat effect estimates, unlike hierarchical linear models.
Area of Science:
- Statistics
- Epidemiology
- Biostatistics
Background:
- Randomized control trials (RCTs) frequently employ clustered designs, randomly assigning intact groups to treatment or control.
- Hierarchical linear models (HLMs) are standard for analyzing such clustered RCTs.
- Limited guidance exists for handling noncompliance due to cluster switching in these designs.
Purpose of the Study:
- To evaluate the impact of cluster switching on intent-to-treat (ITT) effect estimation in clustered RCTs.
- To compare the performance of Hierarchical Linear Models (HLMs) versus linear regression with two-way cluster adjusted standard errors under noncompliance.
Main Methods:
- Analytical derivations and simulations were used to assess bias in ITT estimates.
- Examined the effect of assigning individuals to 'as-assigned' versus 'as-treated' clusters within HLMs.
- Investigated linear regression with two-way cluster adjusted standard errors as an alternative.
Main Results:
- Using 'as-treated' clusters in HLMs biases ITT effect estimates.
- Using 'as-assigned' clusters in HLMs biases standard error estimates when treatment effect heterogeneity exists.
- Linear regression with two-way cluster adjusted standard errors yields unbiased ITT estimates and consistent standard errors.
Conclusions:
- Standard HLM approaches are inadequate for clustered RCTs with noncompliance and cluster switching.
- Linear regression with two-way cluster adjusted standard errors is recommended for accurate ITT effect estimation in these scenarios.
- This method offers a robust alternative for analyzing complex clustered trial data.
Related Concept Videos
01:13Randomized Experiments
8.7K
The randomization process involves assigning study participants randomly to experimental or control groups based on their probability of being equally assigned. Randomization is meant to eliminate selection bias and balance known and unknown confounding factors so that the control group is similar to the treatment group as much as possible. A computer program and a random number generator can be used to assign participants to groups in a way that minimizes bias.
Simple randomization
Simple...
Simple randomization
Simple...
8.7K
02:01Group Design
10.0K
The most basic experimental design involves two groups: the experimental group and the control group. The two groups are designed to be the same except for one difference— experimental manipulation. The experimental group gets the experimental manipulation—that is, the treatment or variable being tested—and the control group does not. Since experimental manipulation is the only difference between the experimental and control groups, we can be sure that any differences between...
10.0K
01:15Bioequivalence Experimental Study Designs: Repeated Measures, Cross-Over, Carry-Over, and Latin Square Designs
116
Body:Bioequivalence experimental study designs play a pivotal role in testing the effectiveness of various treatments. Key among these are the repeated measures, cross-over, carry-over, and Latin square designs. In the repeated measures design, each subject receives all treatments, allowing for temporal comparisons. This type of design is useful in reducing variability but requires careful planning to avoid bias.The cross-over design, an economical method, involves sequential administration of...
116
01:20Cluster Sampling Method
13.8K
Appropriate sampling methods ensure that samples are drawn without bias and accurately represent the population. Because measuring the entire population in a study is not practical, researchers use samples to represent the population of interest.
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
13.8K
01:20Bioequivalence Experimental Study Designs: Completely Randomized and Randomized Block Designs
151
Body:Bioequivalence experimental study designs are crucial methodologies used in evaluating and comparing the bioavailability of different drug products. These designs are categorized into various types: completely randomized, randomized block, repeated measures, cross and carry-over, and Latin square designs.Completely randomized designs involve randomly allocating treatments to all subjects participating in the experiment. This allocation is achieved by assigning unique random numbers to...
151
01:11Blinding
3.8K
Blinding is a commonly used method of not telling participants which treatment a subject is receiving. Blinding is a critical part of a randomized control trial or RCT. It reduces the bias that affects the results. In an RCT, blinding is used in the form of a placebo. A placebo effect occurs when untreated subjects falsely believe they have received the treatment and report improved symptoms. A placebo or a dummy treatment is administered to subjects to negate the bias caused by such an effect.
3.8K