The BLUPs are not βbestβ when it comes t
β
Jeffrey S Morris
π
Article
π
2002
π
Elsevier Science
π
English
β 87 KB
In the setting of mixed models, some researchers may construct a semiparametric bootstrap by sampling from the best linear unbiased predictor residuals. This paper demonstrates both mathematically and by simulation that such a bootstrap will consistently underestimate the variation in the data in ΓΏn