Investigating Science 11–12 · Year 12

Control groups and blinding: a double-blind taste test with a binomial test

Module 7: Fact or Fallacy?

Practical, model not builtLow risk

This site has no interactive model of its own. Where a step or a material names a Concept Studio model, simulation or tool, it has not been built; an external simulation a step names (for example PhET) is not part of this site.

The idea

Blinding, random order and a probability calculation separate a real ability to tell two products apart from chance and from expectation.

Safety card

Low riskAn adult supervises

Hazards

food tasting in a laboratory is prohibited
allergies
shared cups

Controls

run the test in a food-safe room with new cups
check allergies beforehand and allow opting out
record results against codes, not names

Note

No chemicals or heat. Food tasting follows school food-safety procedures outside the laboratory; participants give informed consent. Record the activity in RiskAssess.

What you need

chilled tap water and a bottled still water at the same temperature (or two brands of one plain food), in identical cups
a third person to code the cups, a coin or random number table for order, answer slips
consent forms, allergy check, a food-safe classroom (not a science laboratory)

How to do it

State the claim to test (for example, “people can tell bottled from tap water”) and the null hypothesis.
A third person codes pairs of cups; the server does not know the code (double blind) and each taster’s order is set by coin toss.
Each of 20 tasters names the bottled water; record correct or incorrect.
Run a second, unblinded round with labelled cups and record the answers.
Calculate the probability of getting at least as many correct by chance and decide whether to reject the null hypothesis.
Discuss what placebo effects, expectation and sample size contribute, with reference to clinical trials.

What you should see

Under the null hypothesis each taster is right with probability ½. With 20 tasters, 15 or more correct has probability 0.021 (one-tailed) while 14 or more has 0.058, so 15 is the smallest count that meets p < 0.05. The unblinded round tests whether seeing the label changes the answers, which is the reason trials blind both participants and those running them.

What changes

What you change: blinded or unblinded presentation
What you measure: number of correct identifications out of 20
What you keep the same: same temperature and volume
identical cups
random order
same question to every taster

Common misconceptions

Each of these ideas is wrong, and the activity is a chance to test it.

If most people pick correctly the claim is proven.
Blinding the tasters is enough; the server’s knowledge does not matter.
A small panel that agrees is convincing.

Curriculum references

The NSW syllabus outcomes and Australian Curriculum v9 codes this activity supports. They are references, not a verified or complete curriculum alignment.

Investigating Science Stage 6 Syllabus (2017), NESA; currentINS12-14 INS11/12-4 INS11/12-5 INS11/12-6 INS11/12-7
Australian Curriculum v9No Australian Curriculum v9 code is listed.

Sources

The pages the author read to write this activity.

All Concept Studio activities