Statistics key terms

The probability of a specified event occurring in a particular group, over a stated period where relevant. From collected data, it is estimated by dividing the number of times the event occurs by the total number of observations.

How closely a recorded value agrees with the true value of the quantity being measured.

A boundary beyond which production should be stopped immediately and machinery reset. For sample means, action limits are set at three standard deviations of the sample means above and below the expected value.

The way people or observations are spread across different ages or age groups.

The sum of all numerical data values divided by the number of values.

A relationship between variables; knowing something about one provides information about the other.

Using technology to carry out calculations or other processing tasks automatically, rather than repeating each task by hand.

A value or category used to describe the centre or a typical member of a data set.

The mean of the seasonal variations for the same season across the available cycles. Also called mean seasonal variation.

Another variable or condition that may influence both of the variables being compared.

The reference period whose value is assigned an index of 100 in a fixed-base index series.

A tendency for an outcome to occur more or less often than the assumed fair model predicts, rather than differences arising only through chance.

A probability distribution for the number of successes in a fixed number of independent trials, each having two outcome categories and the same probability of success.

Paired observations of two variables for each person or item being studied.

A diagram showing the minimum, lower quartile, median, upper quartile and maximum of a data set.

A method of estimating population size by capturing and marking a first sample, releasing it, then checking a second sample for marked individuals.

Data consisting of categories, such as preferred pizza topping or method of travel.

A cause-and-effect relationship in which a change in one variable causes a change in another.

The address of a spreadsheet cell, written with its column letter followed by its row number; for example, B2.

A collection of data covering every member of the population being studied.

An event that must happen; its probability is 1, or 100%.

An index comparing a value in one period with its value in the immediately preceding period, which acts as the reference value of 100.

A map or spatial diagram in which regions are shaded or patterned according to the interval containing their data value.

An endpoint separating adjacent intervals of grouped numerical data.

A range of values used to group numerical observations, such as $10 \leq t < 20$.

The value halfway between the two ends of a class interval, used to represent that class when estimating a grouped mean.

The difference between a class's upper and lower boundaries: $\text{class width}=\text{upper boundary}-\text{lower boundary}$.

A population in which births, deaths and movements into or out of the population have negligible effects during the study period.

A question that asks a respondent to choose from a supplied set of answers.

Dividing a population into groups, randomly selecting some groups and including all members of the selected groups in the sample.