Models and Forecasting: 2.2 Econometrics

Econometrics is the means for turning theoretical models into mathematical models which allow forecasts to be made. It is a collection of statistical techniques which can be used to quantify relationships and test economic theory, using past data to create equations. A whole raft of diagnostic tests within these techniques allows economists to test the efficacy of these estimated equations.

Click on the symbols to find out more.
Regression analysis

The main tool used in econometrics is regression analysis.

Regression analysis assumes that the dependent variable is a linear function of one or more independent or explanatory variables plus an error term. The error term is added to take account of all other influences.

If there is just one independent variable, the technique is referred to as simple regression and if more than one independent variables involved it is referred to as multiple linear regression.

Using Excel

Microsoft Excel includes a number of statistical functions, one of which enables users to estimate multiple linear regressions.

This particular package also includes a range of additional statistics permitting equations to be evaluated. For instance, the package estimates the coefficient of determination which measures the degree of relationship between the dependent variable and the explanatory variables.

It provides an 'F' statistic which allows the user to test whether or not the observed relationship occurred by chance and it also allows the user to test the significance of each individual coefficient using 't' statistics.