# What is an error term?

In statistics, an error term is the sum of the deviations of each actual observation from a model regression line. Regression analysis is used to establish the degree of correlation between two variables, one independent and the other dependent, resulting in a line that best “fits” the effectively observed values ​​of the dependent value in relation to the independent variable(s). (s). Put another way, an error term is the term in a model's regression equation that explains and explains the unexplained difference between the actually observed values ​​of the independent variable and the model's predicted outcomes. Therefore, the error term is a measure of how accurately the regression model reflects the actual relationship between the independent and dependent variables. The error term can indicate that the model can be improved, such as adding another independent variable that explains part or all of the difference, or by randomness, which means that the dependent and independent variable(s) ) are not correlated to a greater degree.

Also known as a residual term or perturbation term, according to mathematical convention, the error term is the last term of a model regression equation and is represented by the Greek letter epsilon (ε). Economists and financial industry professionals regularly use regression models, or at least their results, to better understand and predict a wide range of relationships, such as how changes in the money supply are related to inflation, how stock market prices are related to to unemployment. rates or how changes in commodity prices affect specific companies in an economic sector. Therefore, the error term is an important variable to consider and track as it measures the degree to which a given model does not reflect or does not take into account the real relationship between the dependent and independent variables.

There are actually two types of error terms commonly used in regression analysis: absolute error and relative error. The absolute error is the error term as defined above, the difference between the actually observed values ​​of the independent variable and the results predicted by the model. Derived from this, the relative error is defined as the absolute error divided by the exact value predicted by the model. Expressed in percentage terms, the relative error is known as the percentage error, which is useful because it puts the error term in greater perspective. For example, an error term of 1 when the predicted value is 10 is much worse than an error term of 1 when the predicted value is 1 million when trying to get a regression model showing how well two or more are correlated.

Go up