Although only one marker in each high LD cluster was kept for calculating marked variance in order to reduce bias, caution still needs to be exercised when interpreting this variance since it was obtained from unshrunken estimates of marker effects with simple regression approaches.
The number of repetitions needs to be sufficiently large in order to reduce the variance in the prediction error estimate (the more, the better since this reduces variance in the prediction error estimate) [2].
The data did not support this hypothesis since the variance explained by individual SNPs in KORA-F3 was very low also for SNPs which were either genotyped or imputed with high quality (see Supplementary Material, Tables S2 and S3).
This was unexpected since the variance of genomic signatures within genomes has usually been associated with foreign genetic elements like phages and pathogenicity islands [21].
This is reasonable, since the variance of a statistic is inversely related to the information in the data, which in a censored time-to-event sample is plausibly represented by the number of events [ 27].
This was not unexpected, since the variance is likely to increase in pools compared to individual reactions due to additional experimental factors and decreased sequencing depth per sample.
This is a critical step since the variance of the CC estimates increases with increasing order [16].
This may seem counter-intuitive since the variance of breeding values for a base animal is σ a 2 (1 + γ / 2 ).
This is an upper bound since the variance of the ensemble mean would be reduced if a larger ensemble were available.
Members of the Poisson-Tweedie family defined by formula (3) are often used for modeling overdispersed count data, since the variance of a generic member of this class is greater than its mean (compare to formula (4)).
