Unlocking the Power of Bootstrap: Analyzing Small Sample Sizes with Confidence
Course Objectives
By the end of this course, you will be able to:
- Understand the basic principles and assumptions of bootstrap methods
- Apply bootstrap methods to estimate standard errors, confidence intervals, and hypothesis tests for various sample statistics
- Compare and contrast bootstrap methods with traditional parametric methods
- Use software tools such as R or Python to implement bootstrap methods on real data
Course Importance
This course is important for PhD students and working professionals who want to:
- Learn a powerful and flexible statistical technique that can handle small sample sizes and complex data structures
- Overcome the limitations and assumptions of traditional parametric methods
- Enhance their skills and confidence in data analysis and inference
- Contribute to the advancement of science and practice through high-quality research
Course Modules
The course consists of four main modules, each with several subtopics and activities. The modules are:
Module 1: Introduction to Bootstrap Methods
In this module, you will learn how to:
- Define bootstrap methods and their main advantages and disadvantages
- Explain the concept of resampling and sampling with replacement
- Describe the steps involved in performing bootstrap methods
- Identify the types and applications of bootstrap methods
Module 2: Bootstrap Methods for Estimating Standard Errors and Confidence Intervals
In this module, you will learn how to:
- Estimate standard errors and confidence intervals for the mean, median, and other sample statistics using bootstrap methods
- Compare and contrast bootstrap methods with parametric methods such as t-test and z-test
- Evaluate the accuracy and precision of bootstrap estimates
- Choose an appropriate bootstrap method and sample size for your data
Module 3: Bootstrap Methods for Hypothesis Testing
In this module, you will learn how to:
- Perform hypothesis tests for the mean, median, and other sample statistics using bootstrap methods
- Compare and contrast bootstrap methods with parametric methods such as ANOVA and chi-square test
- Interpret the results and conclusions of bootstrap tests
- Assess the power and significance of bootstrap tests
Module 4: Bootstrap Methods for Complex Data Structures
In this module, you will learn how to:
- Apply bootstrap methods to complex data structures such as regression models, time series, and multivariate data
- Use advanced bootstrap techniques such as bootstrapping residuals, block bootstrapping, and bootstrap-after-bootstrap
- Address the challenges and issues of bootstrap methods for complex data structures
- Evaluate the performance and validity of bootstrap methods for complex data structures
Course Assessment
The course assessment will consist of:
- A written assignment on applying bootstrap methods to a real dataset of your choice, following the guidelines and criteria of the course
- A presentation of your assignment to your instructor and peers, using a rubric and feedback form
- A reflection paper on your learning experience and outcomes from the course
Training Cost
The training cost for each module is US$15 per module of your choice. However, we offer discounts if you are interested in ALL modules. The cost is for full remote training, and it covers the tuition fees, learning materials, and certification. Those interested in physical training incur an additional US$25 to include meals and refreshments at the training venue. Further information will be provided upon inquiry.
Application Process
Applicants should complete the LERIS Course-Application-Form.
