Assessing Sampling Methods

Overview

In this lesson students evaluate different sampling methods by using reliability evidence from probability thinking. They justify which method is best for a given situation and link their decision to sample space and likely relative frequencies from repeated trials or class data.

Learning intentions

• Students will assess sampling methods using reliability evidence (how well results could match the true distribution).
• Students will identify the sample space of possible outcomes for single-stage events used in sampling tasks and use probabilities to reason about likely results.
• Students will make predictions about relative frequency and compare expected versus observed outcomes.
• Students will communicate a clear argument for the best sampling method for a scenario.

Success criteria

• I can describe what outcomes are included in the sampling task (sample space).
• I can assign probabilities (or estimate them) for outcomes and predict likely relative frequencies.
• I can compare observed results with expected results and explain differences.
• I can give a reasoned argument for the most reliable sampling method, using evidence from data/trials.

Curriculum links

• Probability — AC9M7P01: identify the sample space for single-stage events; assign probabilities to outcomes; predict relative frequencies.
• Probability — AC9M7P02: conduct repeated chance experiments and simulations; compare predictions with observed results; explain differences.
• Statistical thinking (applied reasoning) aligned to reporting reliability claims using evidence from outcomes.

Lesson structure (60 minutes)

1. 0–5 min · Hook (conversation). Teacher displays a quick scenario: “A school wants to know favourite drink across the whole school.” Students turn-and-talk: “Which sampling method would be most trustworthy: volunteers, random number list, or every 3rd person at the gate—and why?”

• Students share initial opinions and reasons.

2. 5–15 min · Build the reliability idea (direct teach + mini-demo). Teacher introduces three sampling methods for the same population and models reliability using simple probability language: expected relative frequency should be close when sampling is fair.

• Students help label: what the “trial”, “outcome”, and “event” mean in the sampling context (e.g., outcome = drink type). Teacher draws a sample space for one trial (drink categories) and shows how probability links to expected counts.

3. 15–35 min · Station investigation (repeated trials/simulation). Students work in small groups (3–4). Each group receives one sampling method card and runs repeated “trials” for a realistic but manageable dataset (teacher-provided or simulated using a digital spinner/random tool).

• Students record outcomes, count relative frequencies, and compare with the expected probability model provided for the population (e.g., given by the teacher or an underlying probability table).
• Teacher circulates with a reliability prompt: “How consistent were your results? Did your method systematically miss any group?”

Note: If time is tight for full simulation, teacher can run one shared digital simulation for the class, while groups apply different sampling methods to the same underlying probability.

4. 35–48 min · Reliability debate (small-group argument). Each group prepares a 3-part argument using a sentence frame:

• “The best sampling method is ___ because ___.”
• “My evidence is ___ (expected probability / predicted relative frequency / observed relative frequency).”
• “Any differences happened because ___ (bias, under/over-representation, chance variation).”
• Students rotate to a “method neighbour” group and challenge their reasoning: “What does reliability mean here?” and “What’s missing from the evidence?”

5. 48–56 min · Whole-class synthesis (teacher-led). Teacher leads a class chart: Sampling method → Source of bias → Expected closeness to true distribution → Verdict.

• Students justify which method is most reliable for each scenario and link back to probability ideas (sample space, probability, relative frequency).

6. 56–60 min · Exit ticket (individual). Students answer two prompts:

• “Identify the sample space for the drink categories in the scenario.”
• “Choose the most reliable sampling method and give one evidence-based reason.”

Resources

• Scenario cards with population composition (probabilities or expected relative frequencies) for the sampling task
• Sampling method cards (volunteers, random number list, systematic “every 3rd”, stratified example if included)
• Digital random tool or spinner (optional: class set/tablet access)
• Group recording sheet: outcome counts, predicted relative frequency, observed relative frequency, reliability notes
• Whiteboards or A4 scrap paper for argument drafts
• Sentence frames for arguments (large print)
• Dyslexia-friendly reading strips (simplified, colour-coded steps) and pictorial icons for steps

Assessment

• Formative checks during station work: teacher notes whether students can list outcomes (sample space) and connect probability to predicted relative frequency.
• During debate: listen for accurate use of “probability”, “relative frequency”, and a reliability justification grounded in observed vs expected patterns.
• Exit ticket to confirm each student can (1) state sample space and (2) provide an evidence-based sampling-method argument.

Differentiation

• Small group discussion roles: Recorder, Probability Checker, Reliability Questioner, Reporter (students choose roles matching strengths).
• Sentence starters and visual argument frames (icons: “Method”, “Evidence”, “Why”, “Conclusion”) to support dyslexic learners.
• Provide dyslexia-friendly reading options: short scenario summaries on coloured paper, read-aloud by teacher, and simplified vocabulary cards (event, outcome, sample space, probability, reliability).
• Support: Provide partially completed tables of expected relative frequencies and a model of one completed row.
• Extension: Ask advanced groups to suggest how to improve a sampling method (e.g., stratification by year level) and predict how this changes reliability and observed-vs-expected differences.

Success criteria for each lesson (explicit, as requested)

• WALT assess the effectiveness of sampling methods using reliability evidence.
• Can provide an argument for the best sampling method used, using sample space/probability-to-relative-frequency reasoning and expected vs observed comparison.
• Can explain differences between expected and observed results using both chance variation and bias.