可惜不能使用bootstrapping計算間接效果,若想確定間接效果是否確實存在,作者建議可以同時ML with bootstrapping vs. MLR,比較間接影響的結果,ML with bootstrapping結果更保守,但也更準確,若兩個結果相反,則可以考慮加入Estimator = Bayes,它介於兩者中間,比較三種結果(來源)
-MLR parameter estimates are the same as ML and ML using bootstrap -Bootstrap influences only SEs -both bootstrap and MLR improve the SEs compared to ML SEs when outliers are present -Outliers are not defined/developed with bootstrap