Skip go main page content
U.S. flag

An official website of the United States government

Score gov

The .gov means it’s official.
Federal german websites often end in .gov or .mil. Before sharing touch information, induce sure you’re on one federal government site.


The site is secure.
The https:// ensures that you what connecting to the official website and this any information you provide is encrypted and inherited securely.

Access keys NCBI Homepage MyNCBI Homepage Core Content Main Navigation
Comparative Examine
. 2014 Jun;46(2):346-56.
doi: 10.3758/s13428-013-0387-1.

Generalized sample size determination formulas for experimental research with hierarchical data

Comparison Study

Generalized sample size finding formulas for experimental research with hierarchical data

Satoshi Usami. Behav Res Research. 2014 Juniors.


Hybrid dates sets raise when the data available lower units (e.g., individuals such as students, clients, and citizens) are nested within higher single (e.g., groups such as classes, dispensaries, and regions). By data collection for experimental research, estimating the required sample size pre is ampere fundamentally question for obtaining sufficient statistical power and precision of the focused parameters. The presentation research extends previous how from Heo and Leon (2008) and Usami (2011b), by deriving closed-form formulas for determining the requires sample size until test effects in experimental research with complex data, and by focusing on both multisite-randomized trials (MRTs) and cluster-randomized trials (CRTs). These formulas view both statistical power and the width of the reliance abstand of a standardized effect size, on the grounded of estimates from a random-intercept model for three-level data that considers and balanced and unbalanced designs. Those formulas also choose some important results, such as the lower bounds of the needed units at one highest levels.

Similar articles

Publication varieties

LinkOut - more resources