STATISTICAL ASSUMPTIONS AND THEIR IMPACT

INTRODUCTION

In today’s data-driven world, making decisions based on flawed analysis can lead to costly mistakes. While statistical methods are powerful tools, they come with underlying assumptions that, if ignored, can render results misleading or entirely false.

This Statistical Assumptions and Their Impact on Data Analysis course takes a unique and engaging approach to statistical learning. Delivered in the form of a game show called "The Game of Truth and Lies," this highly interactive training experience will challenge delegates to differentiate between valid and misleading analyses.

By exploring data analysis from the basics to inferential statistics, this course equips participants with the skills to critically evaluate statistical results—both their own and those of others. Through real-world examples and hands-on exercises, delegates will learn when statistical techniques can be trusted and when they should be questioned.

This training course will highlight how to:

✔ Understand the fundamental assumptions behind common statistical methods
✔ Recognize how violations of these assumptions impact data analysis
✔ Distinguish between descriptive and inferential statistics
✔ Apply statistical tests for comparing two groups and three or more groups
✔ Identify issues related to multiple comparisons, correlation, and regression
✔ Understand process control and time series forecasting methods
✔ Become more skeptical and critical when evaluating data-driven claims

TRAINING METHODOLOGY

This training course is delivered as an interactive game show—"The Game of Truth and Lies." Instead of traditional lectures, participants engage in problem-solving challenges, quizzes, and real-world case studies that illustrate key statistical concepts.

Through hands-on exercises and team-based competitions, delegates will:

✔ Work through real statistical scenarios to identify valid and misleading conclusions
✔ Apply statistical tests using structured problem-solving techniques
✔ Use a question-and-answer format to reinforce key learning points
✔ Gain practical experience in recognizing errors in data analysis

This highly engaging approach ensures that participants retain knowledge and develop practical skills in statistical analysis and critical thinking.

PERSONAL IMPACT

✔ Enhanced ability to spot misleading statistics in reports and presentations
✔ Greater confidence in applying and interpreting statistical tests
✔ A more skeptical and analytical mindset when reviewing data-driven claims
✔ Stronger practical skills in correlation, regression, and forecasting
✔ Increased proficiency in statistical reasoning and process control techniques

COURSE OUTLINE

The Game of Truth and Lies

Session 1: Introduction and Objectives

✔ Overview of statistical analysis and decision-making
✔ Why understanding assumptions is critical in data interpretation
✔ The role of skepticism in data analysis

Session 2: Data Types and Summary Statistics

✔ Understanding different data types (categorical vs. numerical)
✔ Summary statistics: mean, median, mode, variance, standard deviation
✔ How misleading summaries can distort reality

Session 3: The Normal Distribution

✔ What is the normal distribution, and why is it important?
✔ Identifying skewness and kurtosis
✔ Common mistakes in assuming normality

Session 4: The Central Limit Theorem, p-Values, and Confidence Limits

✔ Understanding the Central Limit Theorem (CLT)
✔ How to correctly interpret p-values
✔ The importance of confidence intervals in decision-making

Session 5: Tests for Two Groups

✔ Comparing two groups: when to use a t-test vs. a non-parametric test
✔ Paired vs. unpaired tests—why does it matter?
✔ The impact of sample size on results

Session 6: Tests for More Than Two Groups

✔ Analysis of Variance (ANOVA)—when to use it
✔ Post-hoc tests and the danger of multiple comparisons
✔ Violations of assumptions and alternative approaches

Session 7: Correlation and Causality

✔ Correlation does not imply causation—how to avoid false conclusions
✔ Identifying spurious correlations
✔ How to test for real causal relationships

Session 8: Regression (Linear, Multiple Linear, Logistic)

✔ Understanding linear regression and its assumptions
✔ The difference between simple and multiple regression
✔ Introduction to logistic regression and classification problems

Session 9: Statistical Process Control

✔ What is process control, and why is it important?
✔ Identifying common cause vs. special cause variation
✔ Control charts and process stability analysis

Session 10: Time Series Forecasting

✔ Introduction to time series analysis
✔ Identifying trends, seasonality, and autocorrelation
✔ Choosing the right forecasting method