Large Data Set

What is the Large Data Set?

The Large Data Set (LDS) is pre-release material published by OCR MEI in advance of Component 02. It is a data set comparable to a set text for a literature course: it can be used as teaching material throughout the course. In the examination it is assumed that learners are familiar with the contexts covered by the data set and that they have used a spreadsheet or other statistical software when working with it.

Learners will not have a printout of the pre-release data set available to them in the examination, but selected data or summary statistics from the data set may be provided within the examination paper.

Recommended activities (from the specification)

1. Exploratory data analysis. Explore the LDS with quantitative and visual techniques to develop insight into underlying patterns and structures, suggest hypotheses to test, and provide a reason for further data collection. This includes creating diagrams, performing statistical calculations and investigating correlation.
2. Modelling. Use the LDS to provide estimates of probabilities for modelling and to explore possible relationships between variables.
3. Repeated sampling. Use the LDS as a model for the population to perform repeated sampling experiments to investigate variability and the effect of sample size.
4. Hypothesis testing. Use the LDS as the population against which to test hypotheses based on your own sampling.