The approaches that capture inconsistency by a single extra variance component in a mixed effects model [ 8, 9] only aim at quantifying inconsistency and at providing conservative confidence intervals.
In English and French, it has also been found that word frequencies based on written texts explain a few percentages of extra variance in visual lexical decision data to those based on film subtitles, even though the written frequencies themselves are inferior to the subtitle frequencies.
The CUSUM measures accumulations of extra variance in a sequential framework, and alarms are signaled when the statistic exceeds a specified threshold.
Another method to assess inconsistency is to set up a mixed model with a sparse covariance structure that allows for one extra variance component to capture inconsistency; this was performed in a classical likelihood framework [ 8] and in a Bayesian framework [ 9, 13].
We used a stepwise multiple regression analysis to investigate whether a combination of frequency measures explained extra variance in the RT data.
However, based on these results, we cannot determine whether the increase in rate of inbreeding in scenarios 1 to 3 compared to the base scenario was caused by IGE or by a reduction in classical heritability due to extra variance.
Finally, the overall effect of intervention was estimated by a random effects logistic regression model, where an extra random effect was included to add extra variance from the observations that were estimated and not observed.
The LRT for one extra variance component is distributed as a mixture of point 0 and 1degrees of freedom (df) [ 46].
To avoid the extra variance caused by resampling while coping with particle degeneracy, a hybrid algorithm is proposed which automatically switches between SIS and APF according to whether a serious decrease in the effective sample size is detected.
This is justified by the Rao-Blackwell theorem which reveals that any redundant random variable present in the estimator will cause extra variance.
On one hand, in view of the extra variance that resampling has inevitably introduced, further studies should be focused on how to circumvent resampling while maintaining an acceptable ESS; On the other hand, novel resampling schemes should be developed to address the trade-off between particle diversity and variance reduction.
