Background:
Intraclass correlation coefficients (ICCs) are used in a wide range of applications.However, most commonly used estimators for the ICC are known to be subject to bias.
Methods:
Using second order Taylor series expansion, we propose a new bias-corrected estimatorfor one type of intraclass correlation coefficient, for the ICC that arises in the context ofthe balanced one-way random effects model. A simulation study is performed to assessthe performance of the proposed estimator. Data have been generated under normal aswell as non-normal scenarios.
Results:
Our simulation results show that the new estimator has reduced bias compared to the leastsquare estimator which is often referred to as the conventional or analytical estimator. Theresults also show marked bias reduction both in normal and non-normal data scenarios. Inparticular, our estimator outperforms the analytical estimator in a non-normal settingproducing estimates that are very close to the true ICC values.
Conclusions:
The proposed bias-corrected estimator for the ICC from a one-way random effectsanalysis of variance model appears to perform well in the scenarios we considered in thispaper and can be used as a motivation to construct bias-corrected estimators for othertypes of ICCs that arise in more complex scenarios. It would also be interesting toinvestigate the bias-variance trade-off.