DSR-081Research DSSTAT
承接上题:percentage RMSE 的 CI 怎么得到(bootstrap);bootstrap 样本量为什么和原样本一样大
📋 题目详细背景与场景
写完了之后问我怎么得出 percentage RMSE(我都没见过这个 metric)的 CI,答“bootstrap”,然后写到一半又说 “Wait a second, why is your bootstrap sample the same sample size as the original sample?” 然后我就说 “Oh, this is quite common and I think it’s the standard procedure of nonparametric bootstrap?” 然后他说“那你是不是有概率得到一个和原来的 sample 一样的 bootstrap sample 呢?”我还以为是考概率题,正准备算,然后面试官说 “Oh actually it’s not very likely. Never mind.”
📖 对应核心知识点手册:
想用苏格拉底式对话深入理解该考点的第一性原理?
进入破冰推演实验室,模拟考官互动并一步步拆解底层机制与直觉陷阱。
⚡
Test muscle memory on this topic via 3-Layer Flashcards
Active Recall: Mentally formulate Prompt ➔ Math Derivation ➔ Benchmark Implementation in 3 minutes.