Mathematics · Grade 9 · Data, Probability, and Decision Making · Term 3

Sampling Techniques and Bias

Students will identify different sampling techniques and recognize potential sources of bias in data collection.

• Ontario Curriculum Expectations
• CCSS.MATH.CONTENT.HSS.IC.B.3
• CCSS.MATH.CONTENT.HSS.IC.A.1

About This Topic

Sampling techniques and bias equip Grade 9 students with tools to collect reliable data. They compare simple random sampling, where every population member has an equal chance, stratified sampling, which divides the population into subgroups, cluster sampling using natural groups, and convenience sampling based on ease of access. Students spot biases like voluntary response, where self-selected participants skew results, non-response when people ignore surveys, and undercoverage missing population segments. These ideas tie to real applications in Canadian election polls and health studies.

In Ontario's data management strand, this topic builds skills to critique methods and justify random sampling for valid population inferences. Students practice explaining how biased samples lead to flawed decisions, a key expectation for probability and decision making.

Active learning excels here because students simulate sampling from classmates or objects, observe bias effects immediately, and refine techniques through group trials. This hands-on approach turns theoretical concepts into practical insights, boosting engagement and retention.

Key Questions

1. Explain how different sampling techniques can lead to representative or biased samples.
2. Critique a given sampling method for potential sources of bias.
3. Justify the importance of random sampling in drawing valid conclusions about a population.

Learning Objectives

• Compare and contrast simple random, stratified, cluster, and convenience sampling techniques, identifying their strengths and weaknesses.
• Analyze a given data collection scenario to identify potential sources of bias, such as voluntary response, non-response, and undercoverage.
• Evaluate the validity of conclusions drawn from a sample, explaining how bias can distort results.
• Justify the use of random sampling methods to ensure a sample is representative of a larger population.
• Design a simple survey using an appropriate sampling technique for a given research question.

Before You Start

Introduction to Data Collection

Why: Students need a basic understanding of what data is and why it is collected before learning about different methods of collection.

Measures of Central Tendency (Mean, Median, Mode)

Why: Understanding how to summarize data is foundational to interpreting the results of a sample and recognizing when those results might be skewed.

Key Vocabulary

Simple Random Sampling	A sampling method where every member of the population has an equal and independent chance of being selected.
Stratified Sampling	A method that divides the population into subgroups (strata) based on shared characteristics, then samples randomly from each subgroup.
Cluster Sampling	A method that divides the population into clusters, then randomly selects entire clusters to sample from.
Convenience Sampling	A sampling method where participants are selected based on their easy availability and accessibility, often leading to bias.
Sampling Bias	Systematic error introduced into sampling when the sample is not representative of the population intended to be analyzed.
Voluntary Response Bias	Bias that occurs when individuals choose whether or not to participate in a survey, often leading to stronger opinions being overrepresented.

Watch Out for These Misconceptions

Common Misconception

Random sampling means picking numbers or people haphazardly.

What to Teach Instead

True random sampling gives each population member an equal, known chance, often using tools like random number generators. Hands-on simulations with numbered cards let students see haphazard picks create bias, while proper randomization evens chances. Group comparisons clarify the difference.

Common Misconception

A large convenience sample eliminates bias.

What to Teach Instead

Size does not fix inherent bias from non-representative access, like polling only school friends for city opinions. Active sampling trials show large biased samples still mismatch population data. Peer discussions help students adjust methods for better representation.

Common Misconception

Voluntary response surveys are unbiased because participants care.

What to Teach Instead

Motivated respondents often hold extreme views, skewing results away from the population. Role-play surveys reveal this as groups with strong opinions dominate. Collaborative analysis builds skills to spot and counter such biases.

Active Learning Ideas

Stations Rotation: Sampling Methods Stations

Set up four stations for simple random (numbered slips drawn from hat), stratified (by height groups), cluster (random class sections), and convenience (ask nearest students). Each small group samples 'favorite lunch' preferences, records results, then rotates and compares sample accuracy to class census.

45 min·Small Groups

Bias Simulation: Dice Roll Surveys

Pairs roll dice to simulate population traits (e.g., 1-3 sporty, 4-6 artistic). One pair uses random picks, the other convenience (first rolls only). Tally and graph results, then discuss why convenience overestimates one trait. Share findings class-wide.

25 min·Pairs

Poll Critique: Real-World Analysis

Whole class reviews three online poll examples (e.g., social media voluntary response). In small groups, identify bias sources and suggest fixes like random digit dialing. Present critiques and vote on most biased poll.

35 min·Small Groups

Jury Duty Role-Play: Stratified Sampling

Assign class roles reflecting community demographics. Groups draw jury panels using stratified vs random methods. Calculate representation matches and debate fairness in a mock trial scenario.

40 min·Small Groups

Real-World Connections

• Market researchers use stratified sampling to ensure their product surveys accurately reflect the demographics of potential customers across different age groups and income levels in cities like Toronto or Vancouver.
• Political pollsters employ various sampling techniques, including random digit dialing and stratified sampling, to gauge public opinion on candidates and issues, aiming for representative samples of eligible voters across Canada.
• Health organizations conduct health surveys using cluster sampling, selecting specific geographic regions or communities to study health trends and outcomes, which can inform public health interventions in provinces like Quebec or Alberta.

Assessment Ideas

Quick Check

Present students with short descriptions of four different sampling scenarios (e.g., surveying people at a mall, randomly selecting names from a phone book, dividing a school into grades and surveying 10 students from each grade). Ask students to identify the sampling technique used in each and one potential source of bias, if any.

Discussion Prompt

Pose the question: 'Imagine you want to find out the most popular extracurricular activity among Grade 9 students in your school. What sampling method would you use and why? What potential biases would you need to watch out for?' Facilitate a class discussion where students share and critique each other's proposed methods.

Exit Ticket

Provide students with a scenario: 'A company wants to know if Canadians prefer their new snack. They set up a booth at a popular music festival and ask attendees to try the snack and fill out a survey.' Ask students to write two sentences explaining why this sampling method might lead to a biased result.

Frequently Asked Questions

What are common sampling techniques in Grade 9 Ontario math?

Key techniques include simple random sampling for equal chances, stratified for subgroup representation, cluster for cost-effective groups, and systematic for ordered lists. Students learn convenience sampling introduces bias. Activities like class surveys help compare methods, showing random and stratified yield truer population snapshots while others falter.

How to identify bias in sampling methods?

Look for voluntary response (self-selecting extremes), non-response (ignores subgroups), undercoverage (misses segments), and question wording (leads answers). Critique by checking if the sample mirrors population diversity. Simulations where students sample classmates expose these issues quickly, fostering critical evaluation skills for real data.

Why is random sampling important for valid conclusions?

It ensures every population member has an equal chance, minimizing bias for accurate inferences. Biased samples, like convenience polls, mislead decisions in policy or business. Ontario curriculum emphasizes justifying random methods; trials with objects or peers demonstrate how it reduces error margins effectively.

How can active learning help teach sampling techniques and bias?

Active methods like station rotations or dice simulations let students collect data hands-on, witness bias in their results, and test fixes collaboratively. This beats lectures by making abstract bias visible, such as skewed convenience samples. Group shares build justification skills, aligning with curriculum expectations for deeper understanding and retention.