Statistics key terms

Pairs of participants with similar relevant characteristics, with one member of each pair in the test group and the other in the control group.

The average value of a distribution, written $\mu$ for a normal distribution.

The arithmetic mean of seasonal variations for the same season or corresponding point in successive cycles; also called estimated mean seasonal variation or average seasonal effect.

A summary of the centre or typical value of a data set, such as the mean, median or mode.

A summary describing how spread out the values in a data set are.

The middle value of ordered data, or the mean of the two middle values when there is an even number of observations.

A recorded value or answer that is absent from a data set.

The class interval containing the greatest frequency in a grouped frequency table.

The value occurring most frequently in a data set. There can be more than one mode, or no mode.

A relationship in which one variable consistently increases, or consistently decreases, as the other increases. The pattern need not be a straight line.

The mean of a fixed number of successive observations, recalculated as the group moves forward through a time series.

A chart with two or more bars side by side for each category, allowing data sets to be compared.

Matched sets of values for three or more variables, recorded for each individual, object or observation. This term is assessed at Higher tier only.

Events that cannot both occur in the same trial. For two mutually exclusive events, $P(A \text{ and } B)=0$.

An investigation of naturally occurring conditions or differences, without the researcher setting or manipulating those conditions.

An association in which larger values of one variable tend to occur with smaller values of the other.

A distribution with a tail towards lower values; values below the median have a greater spread than those above it.

Failure to obtain a response from a selected participant, either to the whole survey or to particular questions.

Bias arising when those who respond differ in relevant ways from those who do not respond.

A probability distribution for continuous quantities with a symmetrical, bell-shaped curve and equal mean, median and mode.

A method of collecting data by watching and recording what happens.

The number of times an event actually occurs in an experiment.

A class interval with no specified lower boundary or no specified upper boundary.

A question that lets a respondent answer in their own words without choosing from a supplied set of answers.

Selecting suitable members of a population who are readily available. Also called convenience sampling.

Data that can be placed in a meaningful order or given a numerical rating scale, such as league positions or satisfaction ratings.

A single possible result of a trial.

An extreme data value that does not fit the general pattern of a dataset.

A calculated limit used to identify outliers: values below the lower limit or above the upper limit are classified as outliers.

Two values belonging to the same person, object or observation, one for each variable.