Glossary

ANOVA:

A statistical technique that helps in making inference for whether three or more samples might come from populations having the same mean; specifically, whether the differences among the samples might be caused by chance variation. ANOVA is used in situations where a single factor is believed to account for differences in the data, and that factor allows us to lump the observations into a small number of discrete categories.

Business metric:

A continuous variable of interest in a data set. A business metric may be used as a dependent or an independent variable.

Business outcome:

The dependent variable you select in a statistical question. You select a single business outcome from the set of business metrics.

Categorical variable:

A variable whose values are a finite, restricted set of enumerated values. Examples might include gender (male or female) or job title (engineer, salesman, manager).

Coefficient of determination:

See R-squared (R2).

Cohort:

A group of people who have a feature in common, particularly being of the same generation or entering a school or a company at the same time.

Continuous variable:

A variable whose values can vary across a broad range. Continuous variables may be either real numbers or integers, or they may fall into a restricted range (such as 0 to 100). Compare with Categorical variable.

Correlation:

A mutual relationship of two or more things. The degree to which two or more attributes or measurements on the same group of elements ...

Get Human Capital Analytics: How to Harness the Potential of Your Organization's Greatest Asset now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.