Linear regression


Also found in: Dictionary, Thesaurus, Medical, Legal, Acronyms, Encyclopedia, Wikipedia.
Related to Linear regression: Multiple linear regression

Linear regression

A statistical technique for fitting a straight line to a set of data points.

Linear Regression

A statistical technique in which one takes a set of data points and plots them on a line. Linear regression is used to determine trends in economic data. For example, one may take different figures of GDP growth over time and plot them on a line in order to determine whether the general trend is upward or downward.
References in periodicals archive ?
The principles involved are shown below of how an INR can be determined with a line estimated by using simple linear regression based, for example, on 5 calibrant plasmas.
There are several variations to regression analysis such as multiple linear regression whereby a dependent variable is associated with more than one independent variable.
So, the final multiple linear regression equation showing linear relationship between business result and strategy is given by:
Although the simple linear regression model relating points per game (PPG) and average rebounds (AVGREBS) revealed the predicted equation of 2.
Linear regression is convenient for determining precisely how much each additional site, or square foot, or income received contributes to sale price or value.
Linear regression is a special case of the least-squares method and it is the most common way of analyzing strength data.
A Multiple Linear Regression Analysis using a constant was computed against scores on the PDT and the present Grade for the 292 High School Students as depicted in Table 2 below.
A linear regression analysis, however, did show a positive lin in children with higher [alpha]-methyl-L-tryptophan uptae ratios in the caudate nuclei whose scores on a behavior and social interaction test suggested autism.
The method of comparison of the residual values from a linear regression is not appropriate for these data as the range of values (all normal donors) was too small for a statistically valid regression analysis to be completed.
Presumably, according to Lott, the way to test this theory would be to do a linear regression involving as many extraneous variables as we can think of that might affect the Nasdaq--and not to worry too much that we may not have gotten them all.