SHARE THE ARTICLE ON
As the name suggests, multiple regression is a statistical technique applied on datasets dedicated to draw out a relationship between one response or dependent variable and multiple independent variables. Form the definition it is obvious that the study of an event or phenomena will have various factors causing its occurrence.
Multiple regression works by considering the values of the available multiple independent variables and predicting the value of one dependent variable.
Example: A researcher decides to study students’ performance from a school over a period of time. He observed that as the lectures proceed to operate online, the performance of students started to decline as well. The parameters for the dependent variable “decrease in performance” are various independent variables like “lack of attention, more internet addiction, neglecting studies” and much more.
A 9 min on-demand demo on how you can convert data into insights.
In case of linear regression, although it is used commonly, it is limited to just one independent and one dependent variable. Apart from that, linear regression restricts to the training dataset and does not predict a non-linear regression.
For the same limitations and to cover them, we use multiple regression. It focuses on overcoming one particular limitation and that is allowing to analyse more than one independent variable.
We will start the discussion by first taking a look at linear regression equation:
y = bx + a
y is a dependent variable we need to find, x is an independent variable. The constants a and b drives the equation. But according to our definition, as the multiple regression takes several independent variables (x), so for the equation we will have multiple x values too:
y = b1x1 + b2x2 + … bnxn + a
Here, to calculate the value of the dependent variable y, we have multiple independent variables x1, x2, and so on. The number of independent variables can grow till n and the constant b with every variable denotes its numeric value. The purpose of the constant a is to denote the dependent variable’s value in case when all the independent variable values turn to zero.
Example: So for above example, the multiple regression equation would be:
y = b1 * attention + b2 * internet addiction + b3 * technology support + … bnxn + a
[Related read: Regression Analysis]
ReconMR increased productivity by 40% & scaled to 5 call centers.
Trusted by Top 50 MR firms globally.
Convenience Sampling: A Researcher’s Guide The Ultimate Guide to Convenience Sampling Get a step-by-step guide for choosing the correct representative sample for survey research. Download
Actify Data Labs to join global Community at AI Summit New York on 11-12 December 2019 Actify Data Labs is delighted to announce it will