Regression analysis is a technique in statistics to identify the relations between one dependent variable and one or more independent variables. Independent variables also called predictors. The regression analysis is an effective way to predict something by a given set of data.
The main sense of this technique easy to understand with examples. Let’s say; you try to predict the income of your company this year. You have a set of data including information about sales, the popularity of your product and the economic factors in your area. Regression analysis helps to estimate the impact of these independent variables on your future income - dependent variable.
The main problem in conducting the study by statisticians is that they sometimes do not take into account the effect of one or more unpredictable factors, which can play the important role in forming the results of research. Regression analysis is a really useful tool to avoid and control such situations because it allows us to control these independent variables by isolating it in the model from each other. One more example to go deeper: the study has shown the impact of coffee consumption on a mortality. The results were deplorable for coffee lovers, but the situation changed after including the fact of smoking people. After the model had been corrected, statisticians isolated the “smoking-people” variable from other independent variables and saw which effect it has. Such a controlling makes researches more accurate and reliable
There are exist many types of regression analysis such as linear regression, logistic regression, polynomial regression and others. The basic types are simple and multiple regression analysis, which differ with the number of independent variables. The simple analysis measures a relationship between one dependent and one independent variable while multiple analysis takes into account two or more independent variables.
Also, take a look through these documents: