# Econometrics - Explained

What is Econometrics?

### What is Econometrics?

Econometrics is the use of quantitative statistical methods and mathematics to forecast or predict future trends on the basis of historical data. It tests the real world data with many statistical tools and then compares it with a theory or hypothesis to determine whether the result confirms the theory or hypothesis or not. Econometrics can be divided into two broad categories theoretical and applied econometrics.

Back to:ECONOMIC ANALYSIS & MONETARY POLICY

## How is Econometrics Used

Today, econometrics is not only used as an academic subject. Rather, it is used by traders, policy makers, students, and economists. The field of econometrics was introduced by Simon Kuznets, R. Frisch and L. Klein. They were awarded Nobel Prize in economics in 1971 for their contribution in the field of economics. Econometricians use quantitative tools and methods to analyses historical data for testing or developing theory or model etc. Econometricians may use different quantitative tools such as probability distribution, covariance, correlation, simple regression, time series analysis, frequency distribution, probability distribution and more methods.

## Simples Scenario of Econometric Testing

Lets assume econometrician want to test income effect. An economist may record publicly available data. He may then develop a hypothesis that an increase in a persons income will lead to an increase in spending. He may use regression or correlation to determine their relationship. Regression will measure how strongly income affects consumption and will determine whether their relationship is significant or not. If you want to analyze the impacts of investment on GDP, you would obtain historical data of investment rates and the corresponding level of GDP. The investment would be your independent variable whereas GDP is a dependent variable. In most cases linear relationship is used where change in one variable causes a change in other variable. You may want to use many explanatory variables in your regression model. A simple regression model is used to analyze the relationship between the dependent and an explanatory variable. You would use multiple regression models to explain the relationship between the dependent and multiple explanatory variables.