Detect outliers for selected traits and trials
Outlier detection in trial mean data is performed using a Bonferroni-Holm test to judge
residuals standardized by the re-scaled Median Absolute Deviation (MAD).
The “Outlier Threshold” refers to the threshold level used by the
Bonferroni-Holm test in the detection of outliers. A lower threshold level
report fewer outliers. As a default a commonly used threshold level of 0.05
is used.
Outliers can be saved, then you will have the option of excluding these measurements while
performing Analysis and Download functions.
Bernal-Vasquez AM, Utz HF, Piepho HP (2016). Outlier detection methods for generalized lattices: a case study on the transition from ANOVA to REML. Theor Appl Genet, 129:787-804. doi: 10.1007/s00122-016- 2666-6
Bernal-Vasquez AM, Utz HF, Piepho HP (2016). Outlier detection methods for generalized lattices: a case study on the transition from ANOVA to REML. Theor Appl Genet, 129:787-804. doi: 10.1007/s00122-016- 2666-6