4 Matching Annotations
  1. Sep 2017
    1. How can we draw many different bootstrap samples from the original sample if each bootstrap sample must contain the same number of cases as the original sample? If we allow every case in the original sample to be sampled only once, each bootstrap sample contains all cases of the original sample, so it is an exact copy of the original sample. Thus, we cannot create different bootstrap samples.

      So, bootstrapping without replacement doesn't allow for ANY bootstrapping regardless of sample size?

    1. Which type of sampling is better here: with or without replacement? Justify your answer.

      With replacement simply has more "bootstrapping" power than without correct? But with a large enough sample is there any other effect replacement or non-replacement has on the "outcome?" Or is the effect insignificant with large enough samples.