Students are given a large dataset of children’s and young adults’ anthropometric data to use to investigate whether particular sets of data are related. The students should present their findings in the form of a report/presentation, with the opportunity to use spreadsheet software to present data.

Overview of task

Students are given a large dataset of children’s and young adults’ anthropometric data to use to investigate whether particular sets of data are related. The students should present their findings in the form of a report/presentation, with the opportunity to use spreadsheet software to present data.

Mathematical strand

Statistics

Prior knowledge

Plotting scatter graphs, lines of best fit, correlation, sampling.

Relevance to Core Maths qualifications

•AQA

•C&G

•Eduqas

•Pearson/Edexcel

•OCR

Suggested approaches

The full dataset is almost 4 000 so students may wish to use samples for their analysis. Students can decide what data they want to compare, or the teacher may want to allocate the data to the students. The task would be suited to pairs or small groups. It would be desirable for students to try to mathematically quantify their findings and ask whether they are in line with initial expectations.

Resources/documentation

In addition to this overview, there are:

• Detailed teacher notes (Word and PDF)

• Student information sheet (Word and PDF)

• Excel spreadsheet containing source data

Relevant digital technologies

Access to Excel spreadsheet or similar spreadsheet software is required.

Possible extensions

The students’ findings could be used to formally derive (or show how they may be derived) the formulae for least squares regression line and PPMCC.

Acknowledgement

This resource was developed by the Nuffield Foundation for the FSMQs. It can be accessed at http://www.nuffieldfoundation.org/fsmqs/level-3-data-analysis#Anthropometric%20data