Types of data: raw, quantitative, qualitative, categorical, ordinal, discrete, continuous, ungrouped, grouped, bivariate and multivariate; primary versus secondary; explanatory and response variables; grouping into class intervals.

What this dot point is asking

Edexcel codes 1b.01 to 1b.04 require you to classify data correctly and to know why the classification matters. You must apply the full vocabulary (raw, quantitative, qualitative, categorical, ordinal, discrete, continuous, ungrouped, grouped, bivariate and, at Higher tier, multivariate), distinguish primary from secondary data, use the terms explanatory and response variable, and understand the effect of grouping numerical data into class intervals. The data type decides which diagrams and averages are valid later, so this is a recurring first step.

Quantitative and qualitative

Edexcel notes that more than one term may apply to the same data, so be ready to give several labels. For example, the finishing position in a race is quantitative, discrete and ordinal.

Discrete and continuous

Quantitative data splits into two types:

• Discrete data is counted and takes only particular values, usually whole numbers: the number of pets, goals scored, people in a car.
• Continuous data is measured and can take any value within a range: height, mass, time, temperature. Continuous values are limited only by the precision of the measuring instrument.

The classic exam trap is calling a count continuous. If you can have "half" of it meaningfully (half a second), it is continuous; if not (half a goal makes no sense), it is discrete.

Categorical, ordinal and other terms

• Categorical data sorts items into groups with no inherent order: eye colour, nationality, type of pet.
• Ordinal data is categorical but has a natural order: dress sizes (small, medium, large), exam grades, finishing positions.
• Raw data is data as first collected, before any processing.
• Ungrouped data lists individual values; grouped data is collected into class intervals.
• Bivariate data records two variables for each item (height and mass), which suits a scatter diagram. Multivariate data (Higher tier) records more than two.

Primary and secondary data

Primary data fits your exact question and is up to date, but it is slow and costly to gather. Secondary data is quick and cheap but may not match your question, may be out of date, and may contain errors. Edexcel stresses that sources of secondary data must always be acknowledged, and that you should consider the reliability and accuracy of the data (including rounding) and any constraints on accessing it.

Explanatory and response variables

In an investigation with two variables, the explanatory (independent) variable is the one thought to cause or explain change, and the response (dependent) variable is the one that responds. On a scatter diagram the explanatory variable goes on the $x$ axis and the response variable on the $y$ axis. For example, in "does fertiliser increase plant growth?", fertiliser is explanatory and growth is the response.

Grouping into class intervals

Grouping numerical data into class intervals (code 1b.02) makes a large data set manageable and easier to display, and is essential for histograms and grouped tables. The cost is a loss of accuracy: once values are grouped you no longer know the individual figures, so the mean and other statistics calculated from grouped data are estimates. You should know the term class width and be able to explain this trade-off.