Resampling Two

Question 1

describe a bootstrap resample

Answer 1

works with a single group

can be used to calculate standard error of the mean and confidence interval of a mean

also nonparametric

all possible combinations of the data to make the group size - a participants data might be used once, multiple times or not at all in a sample

Question 2

pros of bootstrap sampling

Answer 2

very general - can use many models for many studies

can be used to perform hypothesis testing

not based on any data assumptions

no tables or hard equations etc

Question 3

how many resamples must you generate ideally

Answer 3

1000-10000 but this is limited by population size

Question 4

describe jackknife resampling

Answer 4

similar to bootstrap but done by ‘selecting all data except one’ rather than ‘randomly sampling by replacement’

Question 5

describe monte carlo method of resampling

Answer 5

create data based on model simulations and compare these to real data