Forecasting is an important concept in econometric and data science. It is also widely used in artificial intelligence and risk management by quantitative analysts, statistical modellers and technologists. Additionally, a large number of studies are carried out to understand and predict variables and their future movements.
Please read disclaimer before proceeding.
Predictive analysis is a black art. There are many right answers.
This article focuses on the concept of regression analysis. In particular, I have divided the article into 6 parts.
- Explanation Of Regression Analysis
- 3 Steps Of Regression Analysis
- Understanding Of Residuals
- Ordinary Least Square Explanation
- Overview Of Model Criterion
One of the most famous methodologies to forecast a variable’s behaviour is to use regression analysis. This technique requires formulating a mathematical equation/model that can be used to give us an estimated value which is as close as possible to the actual observed value.
Regression analysis process is primarily used to explain relationships between variables and help us build a predictive model. Moreover, it can explain how changes in one variable can be used to explain changes in other variables. Regression analysis could be linear or non-linear.
Regression analysis is all about projecting a dependent variable on a set of one or more predetermined independent variables.
Understanding regression analysis is important when we want to model relationships between variables. It can help us understand how close our calculations are to reality. Regression analysis is a simple yet powerful technique.