# Econometric Methods

Definition: The Econometric  Methods make use of statistical tools and economic theories in combination to estimate the economic variables and to forecast the intended variables.

The econometric model can either be a single-equation regression model or may consist a system of simultaneous equations. In most commodities, the single-equation regression model serves the purpose.

But, however, in the case where the explanatory economic variables are so interdependent or interrelated to each other that unless one is defined the other variable cannot be determined, a single-equation regression model does not serve the purpose. And, therefore in such situation, the system of simultaneous equations is used to forecast the variable.

The econometric methods are comprised of two basic methods, these are:

1. Regression Method: The regression analysis is the most common method used to forecast the demand for a product. This method combines the economic theory with statistical tools of estimation. The economic theory is applied to specify the demand determinants and the nature of the relationship between product’s demand and its determinants. Thus, through an economic theory, a general form of a demand function is determined. While the statistical techniques are applied to estimate the values of parameters in the projected equation.

Under the regression method, the first and the foremost thing is to determine the demand function. While specifying the demand functions for several commodities, one may come across many commodities whose demand depends by or large, on a single independent variable. For example, suppose in a city, the demand for items like tea and coffee is found to depend largely on the population of the city, then the demand functions of these items are said to be single-variable demand functions.

On the other hand, if it is found out that the demand for commodities like sweets, ice-creams, fruits, vegetables, etc., depends on a number of variables like commodity’s own price, the price of substitute goods, household incomes, population, etc. Then such demand functions are called as multi-variable demand functions.

Thus, for a single variable demand function, the simple regression equation is used while for multiple variable functions, a multi-variable equation is used for estimating the demand for a product.

2. Simultaneous Equations Model: Under simultaneous equation model, demand forecasting involves the estimation of several simultaneous equations. These equations are often the behavioral equations, market-clearing equations, and mathematical identities.

The regression technique is based on the assumption of one-way causation, which means independent variables cause variations in the dependent variables, and not vice-versa. In simple terms, the independent variable is in no way affected by the dependent variable. For example, D = a – bP, which shows that price affects demand, but demand does not affect the price, which is an unrealistic assumption.

On the contrary, the simultaneous equations model enables a forecaster to study the simultaneous interaction between the dependent and independent variables. Thus, simultaneous equation model is a systematic and complete approach to forecasting. This method employs several mathematical and statistical tools of estimation.

The econometric methods are most widely used in forecasting the demand for a product, for a group of products and the economy as a whole. The forecast made through these methods is more reliable than the other forecasting methods.