LWB Level 3 Experiments 3.11 Learning Workbook

The LWB Level 3 Experiments 3.11 Learning Workbook is a comprehensive, write-on resource designed for the NCEA Level 3 Internal Assessment: Investigate situations that involve elements of chance. This workbook guides students through the principles of experimental design, focusing on the ability to determine whether a "treatment" truly causes a change in a "response" through the use of randomized controlled trials.

Key Features

• The Experimental Design Cycle: A structured walkthrough of the PPDAC cycle adapted for experiments.

  • Problem: Defining a clear, measurable research question (e.g., "Does listening to classical music improve short-term memory?").

  • Plan: Identifying the Explanatory Variable (the thing you change) and the Response Variable (the thing you measure).

• The "Gold Standard" of Testing: Intensive focus on the core components of a valid experiment:

  • Randomisation: Learning why and how to randomly assign participants to groups to ensure that "lurking variables" are evenly distributed.

  • Control Groups: Understanding the necessity of a baseline group to compare results against.

  • Blinding: Exploring the use of single-blind and double-blind techniques to prevent participant or researcher bias.

  • Placebos: Learning how to use "fake" treatments to account for the psychological effect of receiving an intervention.

• Managing Variables: Strategies for identifying and controlling for extraneous variables that could "muddy" the results. Students learn the difference between Experiments (where you intervene) and Observational Studies (where you simply watch).

Analysis & Statistical Reasoning

• Box Plots and Visual Evidence: Practical practice in using NZGrapher to compare the distributions of the control group versus the treatment group.

• The Median Difference: Learning to calculate the difference between the centers of the two groups as a starting point for analysis.

• Re-randomisation (Bootstrapping): A central Level 3 concept. Students use software to simulate "shuffling" the data thousands of times to determine if the observed difference could have happened by pure chance.

  • The P-Value (Tail Proportion): Understanding how to interpret the results of a re-randomisation test. If the observed difference is very rare in the simulation, we have evidence that the treatment actually worked.

• Conclusion and Generalisation: Learning to write a sophisticated summary that discusses whether the findings can be applied to the wider population or if they are limited to the specific participants in the study.

Workbook Highlights

• Internal Assessment Scaffolding: Provides a clear report-writing template that aligns with the requirements for Achievement, Merit, and Excellence.

• NZGrapher Integration: Step-by-step instructions and screenshots on how to perform re-randomisation tests and generate high-quality statistical graphs.

• Real-World Case Studies: Includes diverse experimental contexts—from sports science and psychology to agricultural testing—to help students practice analysis on authentic data sets.

• Critiquing Existing Research: Exercises designed to sharpen "statistical literacy" by identifying flaws in poorly designed experiments (e.g., lack of randomisation or small sample sizes).

• Full Answer Appendix: Provides model answers for the analysis and conclusion sections, demonstrating the required level of depth and technical justification.

• Glossary of Experimental Terms: A complete guide to essential vocabulary—such as Confounding Variable, Re-randomisation Distribution, and Statistical Significance—to ensure students use professional language in their reports.