Bootstrapping: An Integrated Approach with Python and Stata, by Felix Bittmann, is a great resource for students and researchers who want to learn and apply bootstrap methods.
The text begins with a clear introduction to foundational statistics on which bootstrapping methods rely. Bittmann then walks users through the logic behind bootstrapping as well as the process. The book includes discussion of confidence intervals and hypothisis testing as well as a chapter focused on bootstrap considerations related to regression models.
The final chapter demonstrates how researchers can perform bootstrapping using Stata and Python. Examples range from straightforward use of Stata’s bootstrap prefix and vce(bootstrap) option to more advanced techniques such as writing a program for resampling residuals. With this knowledge, readers will be ready to apply bootstrapping in their own analyses using Stata.
BASIC STATISTICAL CONCEPTS
Testing for normality
Probability density functions
Bias and variance
Normality and confidence intervals revisited
Distribution of bootstrap-results
Rate of convergence
The logic of bootstrapping
Failures of the bootstrap
Bias corrected intervals (BC)
Bias corrected and accelerated intervals (BCa)
Summary and simulation
The logic of hypothesis tests
Sampling in accordance with the null
Paired permutation tests
Boot or permute?
Dealing with outliers
Predicting outcomes and bagging
APPLIED PROGRAMMING EXAMPLES
All confidence intervals
Writing own programs
Longitudinal and cluster analyses