A graphic depiction of a bivariate distribution.

Detecting and resolving errors in coding and data entry.

Examples are Cramer’s phi and the correlation coefficient.

The most commonly used statistical measure of variation.

Rejected when a statistical test is significant.

Simultaneously controls for the effects of several independent variables.

Replacing missing values in data analysis by estimating values from the available data.

Indicates how much the dependent variable changes for every one-unit increase in the independent variable.

Consists of editing, coding, data entry, and data cleaning.

A cleaning technique that can be programmed for automatic detection in computer-assisted interviewing.

The value or category in a distribution with the highest frequency.

A graphic display of a univariate distribution.

Back to top