multiple-regression
UK[ˈmʌltɪpl rɪˈɡreʃn]US[ˈmʌltɪpl rɪˈɡreʃn]
n
A statistical technique that models the relationship between a dependent variable and two or more independent variables.
Morpheme Breakdown
multiple
regression
multiple
many
regression
statistical process
Etymology
The term is a modern scientific compound, fusing two Latinate roots to describe a complex analytical concept. 'Multiple' originates from the Latin multus (much, many) combined with the suffix -plex (fold), evolving to signify anything consisting of many parts. 'Regression' derives from the Latin regredi (to go back), from re- (back) and gradi (to step). In statistics, coined by Sir Francis Galton in the 19th century, 'regression' metaphorically described the tendency of extreme measurements to revert or "go back" toward the average. Combined, 'multiple-regression' logically denotes an analytical process that models how a single outcome "goes back" or depends on many contributing factors.
Analysis
Structure: multiple (many) + regression (statistical process)
- multiple: From Latin multiplex (having many folds, manifold). In this compound, it functions as an adjective meaning "involving many."
- regression: From Latin regressus (a going back, return). In this compound, it functions as a noun referring to a specific statistical method of analysis.
Examples
The researcher used multiple-regression to determine which factors most influenced consumer spending.
A multiple-regression analysis can help isolate the effect of advertising from other variables like seasonality and price changes.
The results of the multiple-regression model were presented with several predictor variables.